MCP Server
Retro Diffusion Pixel Art
ai.retrodiffusion/pixel-art
What this MCP does
Generates pixel-art sprites, animations, and tilesets.
Capabilities
Tools
33
tools
authenticate
Authenticate
Authenticate this MCP session with a RetroDiffusion public API key.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['api_key'], 'properties': {'api_key': {'type': 'string', 'description': 'RetroDiffusion API key (rdpk-...), created free at https://retrodiffusion.ai/app/devtools.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
create_inference
Generate Pixel Art
Generate images using the public /v2/inferences endpoint.
For the highest quality prefer RD Pro styles (rd_pro__*); they support reference_images for
character/style consistency, and most go as small as 12x12 px (check list_available_styles
for each style's limits) â a small target size is never a reason to switch to a cheaper
model family. Style ids are opaque strings with no uniform format (some RD Fast styles
appear as "default:rd_flux"); take them verbatim from the catalog and never infer
capabilities from an id's prefix. For animation styles prefer start_inference_job +
get_inference_job instead â animations are long-running, and a failed animation is worth
one retry with identical parameters (failures auto-refund).
Field-tested workflow rules: N distinct items = N individually usable images (separate
calls or num_images=N), never one sheet/grid image unless a sheet IS the deliverable.
Variants of ONE image (seasons, day/night, palettes) = generate the base once, then derive
each variant with the image_edit tool ("... keep the exact same composition") â independent
generations of the "same" scene come out unrelated. Converting an existing image INTO pixel
art is rd_pro__pixelate with input_image (16-256 px output, batch<=16);
reference_images-based generation re-imagines rather than converts. To animate an image you already have, use rd_advanced_animation__*
with input_image (fixed-format rd_animation__* styles generate their own subject from the
prompt instead). To get the other directional views of a sprite you already have, use
rd_advanced_animation__rotate with input_image (same 8-direction layout as rd_animation__8_dir_rotation).
Use `input_image` for the main source image, `reference_images` for extra per-inference
guidance, and `style_reference_images` only on create_user_style/update_user_style.
The response excludes raw base64 image payloads to keep MCP outputs compact.
Open world
Input schema
{'type': 'object', 'required': ['prompt', 'prompt_style', 'width', 'height'], 'properties': {'seed': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Seed for reproducible results; reuse the same seed to iterate on one composition.'}, 'width': {'type': 'integer', 'description': "Output width in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage. Genre-native sizes per item: Minecraft 16; items/icons/props 32-64; character sprites 16-48 retro or 96-128 showcase; tiles 16-32; portraits 96-128; full scenes 256 (RD Pro's max; 16:9 scenes = 256x144 â\x80\x94 pixel art integer-upscales losslessly)."}, 'height': {'type': 'integer', 'description': 'Output height in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.'}, 'prompt': {'type': 'string', 'description': "Describe the SUBJECT only, richly and concretely ('a squat round flask of glowing crimson liquid, cork stopper, bright highlight on the upper-left rim' beats 'a potion'). Never write 'pixel art' â\x80\x94 the selected style handles all rendering. For standalone assets, state a flat background color that contrasts the subject (default 'on a plain white background') and pair with remove_bg=true; never write 'transparent background' (that is remove_bg's job), and never leave the background unstated (it drifts to drab dark gray). Scenes instead describe their real environment. For rd_advanced_animation__rotate the prompt is only an optional hint describing the uploaded subject â\x80\x94 a few words or an empty string."}, 'tile_x': {'type': 'boolean', 'default': False, 'description': 'Make the result tile seamlessly on the horizontal axis.'}, 'tile_y': {'type': 'boolean', 'default': False, 'description': 'Make the result tile seamlessly on the vertical axis.'}, 'strength': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': 'How strongly to change input_image, 0-1 (default 0.75). Lower values keep more of the original.'}, 'remove_bg': {'type': 'boolean', 'default': False, 'description': "Remove the background for transparent output. Use true for standalone assets and pair it with a stated contrasting background in the prompt ('on a plain white background') â\x80\x94 removal works best on flat contrasting backdrops. Animations inherit the start frame's transparency automatically."}, 'num_images': {'type': 'integer', 'default': 1, 'description': 'How many images to generate in one batch; a batch produces varied takes of one prompt (the right way to get N distinct items as individually usable images â\x80\x94 never pack N items into a single sheet/grid image unless a sheet IS the deliverable). Style-specific maximums apply.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}, 'input_image': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': "Base64 PNG used as the main source image for edits, variations, tilesets, animations, or styles that require a starting frame. Raw base64 or a data URL. Send the NATIVE-resolution image: an upscaled display copy (e.g. a 96px sprite exported at 4x = 384px) exceeds style ranges and gets rejected â\x80\x94 downscale to the true pixel grid first. For advanced animations the frame's dimensions must equal width/height, and sprites whose opaque pixels touch the canvas edge animate badly (pad onto a larger transparent canvas first, e.g. 48x48 content onto 64x64)."}, 'extra_prompt': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Secondary prompt for styles that use one (e.g. the transition texture in advanced tilesets).'}, 'prompt_style': {'type': 'string', 'description': "Style id from list_available_styles (e.g. 'rd_fast__default', 'rd_pro__isometric', or a custom 'user__...' style)."}, 'input_palette': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Base64 image of a color palette; output colors are constrained to it.'}, 'upload_outputs': {'type': 'boolean', 'default': True, 'description': 'Host outputs and return URLs in output_urls (recommended for MCP clients) instead of only base64 payloads.'}, 'frames_duration': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Animation frame count for animation styles: 4, 6, 8, 10, 12, or 16. Pick deliberately: 8 is the sweet spot for loops (walking, idle), 6 for a snappy single action, 10-12 for flowing ambient motion. Ignored by rd_advanced_animation__rotate (always 8 views).'}, 'timeout_seconds': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': 'Read-timeout override in seconds for this call; increase for animations or large batches.'}, 'reference_images': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'default': None, 'description': 'Extra per-inference guidance images (base64), only for styles where supports_reference_images is true. Not for defining custom styles.'}, 'extra_input_image': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced).'}, 'return_pre_palette': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Also return the render from before palette constraints were applied.'}, 'return_spritesheet': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'For animation styles: return a PNG sprite sheet instead of a GIF (for rd_advanced_animation__rotate, the 3x3 direction sheet whose views face the center).'}, 'return_non_bg_removed': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Also return the render from before background removal was applied.'}, 'upscale_output_factor': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Integer upscale factor for the output image; 1 returns the native pixel size.'}, 'bypass_prompt_expansion': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Skip the automatic LLM prompt enrichment and use the prompt verbatim.'}, 'include_downloadable_data': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Include extra structured assets when available (e.g. tileset atlas JSON, animation frame data).'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
create_user_style
Create Custom Style
Create a user style from the public RD Pro template using /v2/styles.
Use `style_reference_images` and `style_reference_caption` for style-level references.
These are baked into the custom style and are not the same as per-inference `reference_images`.
Open world
Input schema
{'type': 'object', 'required': ['name'], 'properties': {'name': {'type': 'string', 'description': 'Display name for the custom style.'}, 'min_width': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Force a fixed width (96-256); must be provided together with min_height.'}, 'min_height': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Force a fixed height (96-256); must be provided together with min_width.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}, 'style_icon': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': "Icon name for the style (e.g. 'sparkles')."}, 'description': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Short description of the custom style.'}, 'force_palette': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Always apply palette constraining for this style.'}, 'force_bg_removal': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Always remove backgrounds for this style.'}, 'llm_instructions': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Instructions for the prompt-expansion LLM when this style is used.'}, 'reference_images': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'default': None, 'description': 'Alias for style_reference_images on this tool; prefer style_reference_images and never provide both.'}, 'reference_caption': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Alias for style_reference_caption on this tool; prefer style_reference_caption and never provide both.'}, 'apply_prompt_fixer': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Let the API tidy prompts automatically for this style (default true).'}, 'user_prompt_template': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Prompt template for the style; must contain the {prompt} token.'}, 'style_reference_images': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'default': None, 'description': 'Style-level reference image(s), base64, baked into the custom style (max 1 via the public API).'}, 'style_reference_caption': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Caption describing the style reference image(s).'}, 'expanded_llm_instructions': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Extended instructions for the prompt-expansion LLM.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
delete_lowpoly_animation
Delete Low-Poly Animation
Delete one animation from a Low-Poly model's version (free) and return the model. The rig stays, so animating
again needs no new rig. This cannot be undone.
Destructive
Open world
Input schema
{'type': 'object', 'required': ['asset_id', 'version', 'animation'], 'properties': {'version': {'type': 'integer', 'description': 'The version the animation belongs to.'}, 'asset_id': {'type': 'string', 'description': 'asset_id returned by start_lowpoly_generate or get_lowpoly_job.'}, 'animation': {'type': 'string', 'description': "The animation's name, as listed on the version."}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
delete_user_style
Delete Custom Style
Delete a user style using /v2/styles/{style_id}.
style_id can be either internal id or prompt_style/public_id.
Destructive
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['style_id'], 'properties': {'style_id': {'type': 'string', 'description': 'Style id â\x80\x94 the internal id or the prompt_style/public id (e.g. user__mystyle_ab12).'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
estimate_edit_tool_cost
Estimate Edit Cost (Free)
Validate an edit-tool request and estimate its cost and duration without running it. Always free.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['tool_id', 'input_image'], 'properties': {'width': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'k_centroid_downscale: target width in pixels (required for that tool).'}, 'height': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'k_centroid_downscale: target height in pixels (required for that tool).'}, 'prompt': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'What to generate or change (required by image_edit and inpainting; optional for outpainting).'}, 'tile_x': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'seam_tiling: repair the horizontal seam (tool default applies when omitted).'}, 'tile_y': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'seam_tiling: repair the vertical seam (tool default applies when omitted).'}, 'tool_id': {'type': 'string', 'description': 'Edit tool id. One of: image_edit, inpainting, outpainting, seam_tiling, background_remover, color_style_transfer, color_reducer, palette_converter, pixel_correction, k_centroid_downscale, rotate. Use list_edit_tools for authoritative fields, costs, and limits.'}, 'expand_top': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Outpainting: pixels to add on the top edge.'}, 'mask_image': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Base64 mask for inpainting: white pixels are regenerated, black pixels are kept.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}, 'seam_width': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'seam_tiling: width in pixels of the seam band to repair.'}, 'color_count': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'color_reducer: target number of colors.'}, 'dither_mode': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'color_reducer/palette_converter: dithering mode.'}, 'expand_left': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Outpainting: pixels to add on the left edge.'}, 'input_image': {'type': 'string', 'description': 'Base64 PNG of the image to edit (raw base64 or a data URL). Required by every edit tool.'}, 'expand_right': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Outpainting: pixels to add on the right edge.'}, 'soft_inpaint': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Inpainting/outpainting: blend edits softly with the surrounding pixels.'}, 'expand_bottom': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Outpainting: pixels to add on the bottom edge.'}, 'input_palette': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Base64 image of a color palette; output colors are constrained to it.'}, 'dither_strength': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': 'color_reducer/palette_converter: dithering strength, 0-10 (0 disables, default 5).'}, 'timeout_seconds': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': 'Read-timeout override in seconds for this call; increase for animations or large batches.'}, 'rotation_degrees': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': 'rotate: rotation angle in degrees (clean-edge pixel rotation).'}, 'extra_input_image': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced).'}, 'force_solid_pixels': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'background_remover: force fully solid or fully transparent pixels (tool default applies when omitted).'}, 'repair_window_size': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'seam_tiling: size of the repair window.'}, 'transparency_threshold': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'background_remover: alpha threshold for treating pixels as transparent.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
estimate_inference_cost
Estimate Cost (Free)
Estimate generation cost using the public /v2/inferences endpoint with check_cost=true.
Use `input_image` for the main source image, `reference_images` for extra per-inference guidance,
and `style_reference_images` only on create_user_style/update_user_style.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['prompt', 'prompt_style', 'width', 'height'], 'properties': {'width': {'type': 'integer', 'description': "Output width in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage. Genre-native sizes per item: Minecraft 16; items/icons/props 32-64; character sprites 16-48 retro or 96-128 showcase; tiles 16-32; portraits 96-128; full scenes 256 (RD Pro's max; 16:9 scenes = 256x144 â\x80\x94 pixel art integer-upscales losslessly)."}, 'height': {'type': 'integer', 'description': 'Output height in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.'}, 'prompt': {'type': 'string', 'description': "Describe the SUBJECT only, richly and concretely ('a squat round flask of glowing crimson liquid, cork stopper, bright highlight on the upper-left rim' beats 'a potion'). Never write 'pixel art' â\x80\x94 the selected style handles all rendering. For standalone assets, state a flat background color that contrasts the subject (default 'on a plain white background') and pair with remove_bg=true; never write 'transparent background' (that is remove_bg's job), and never leave the background unstated (it drifts to drab dark gray). Scenes instead describe their real environment. For rd_advanced_animation__rotate the prompt is only an optional hint describing the uploaded subject â\x80\x94 a few words or an empty string."}, 'strength': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': 'How strongly to change input_image, 0-1 (default 0.75). Lower values keep more of the original.'}, 'num_images': {'type': 'integer', 'default': 1, 'description': 'How many images to generate in one batch; a batch produces varied takes of one prompt (the right way to get N distinct items as individually usable images â\x80\x94 never pack N items into a single sheet/grid image unless a sheet IS the deliverable). Style-specific maximums apply.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}, 'input_image': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': "Base64 PNG used as the main source image for edits, variations, tilesets, animations, or styles that require a starting frame. Raw base64 or a data URL. Send the NATIVE-resolution image: an upscaled display copy (e.g. a 96px sprite exported at 4x = 384px) exceeds style ranges and gets rejected â\x80\x94 downscale to the true pixel grid first. For advanced animations the frame's dimensions must equal width/height, and sprites whose opaque pixels touch the canvas edge animate badly (pad onto a larger transparent canvas first, e.g. 48x48 content onto 64x64)."}, 'extra_prompt': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Secondary prompt for styles that use one (e.g. the transition texture in advanced tilesets).'}, 'prompt_style': {'type': 'string', 'description': "Style id from list_available_styles (e.g. 'rd_fast__default', 'rd_pro__isometric', or a custom 'user__...' style)."}, 'input_palette': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Base64 image of a color palette; output colors are constrained to it.'}, 'frames_duration': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Animation frame count for animation styles: 4, 6, 8, 10, 12, or 16. Pick deliberately: 8 is the sweet spot for loops (walking, idle), 6 for a snappy single action, 10-12 for flowing ambient motion. Ignored by rd_advanced_animation__rotate (always 8 views).'}, 'timeout_seconds': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': 'Read-timeout override in seconds for this call; increase for animations or large batches.'}, 'reference_images': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'default': None, 'description': 'Extra per-inference guidance images (base64), only for styles where supports_reference_images is true. Not for defining custom styles.'}, 'extra_input_image': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced).'}, 'return_pre_palette': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Also return the render from before palette constraints were applied.'}, 'return_spritesheet': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'For animation styles: return a PNG sprite sheet instead of a GIF (for rd_advanced_animation__rotate, the 3x3 direction sheet whose views face the center).'}, 'return_non_bg_removed': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Also return the render from before background removal was applied.'}, 'upscale_output_factor': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Integer upscale factor for the output image; 1 returns the native pixel size.'}, 'bypass_prompt_expansion': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Skip the automatic LLM prompt enrichment and use the prompt verbatim.'}, 'include_downloadable_data': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Include extra structured assets when available (e.g. tileset atlas JSON, animation frame data).'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
estimate_lowpoly_cost
Estimate Low-Poly Job
Price a Low-Poly job without starting it (free). For generate with size auto, returns the size auto would pick.
style prices a generate in that style (Lite styles cost less); other operations use the model's own style.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'properties': {'size': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Cube size in texels: "16", "32", "64", "128", "256", or "auto" (default). Auto reads the prompt; reference-image-only requests default to 64. Bigger sizes cost more (see get_lowpoly_pricing).'}, 'style': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Low-Poly style id: rd_lowpoly__detailed (default, free-form shapes), rd_lowpoly__blocky (boxes only, tilted where needed, Minecraft-like), their Lite versions rd_lowpoly__detailed_lite / rd_lowpoly__blocky_lite (a lighter model: simpler results for much less, and Lite prices for everything done to the model later), or another style listed by get_lowpoly_pricing (each style lists its prices).'}, 'prompt': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'What to build or change, up to 250 characters.'}, 'asset_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Required for revise, animate, split and rerig.'}, 'operation': {'type': 'string', 'default': 'generate', 'description': 'generate, revise, animate, split or rerig.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
export_lowpoly_model
Export Low-Poly Model
Export a Low-Poly model for an engine or tool and return a hosted download URL (free).
Engines (Godot, Unity, Unreal, three.js) and Blender get .glb; Blockbench gets .bbmodel; Minecraft gets a
resource pack; .glb and .bbmodel include every animation. Animated GIFs, sprite sheets and MP4 videos need an
animation name from the model.
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['asset_id', 'target'], 'properties': {'target': {'type': 'string', 'description': 'godot, unity, unreal, web, blender (all .glb), blockbench (.bbmodel), obj (zip), minecraft (resource pack zip), atlas (png), turntable (png), axis_views (zip of 6 pixel-exact PNGs, one per axis direction), gif, sheet or mp4 (1024px video) (need an animation). The .glb and .bbmodel files include every animation.'}, 'version': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Version number to work on (default: the newest). Revisions create versions; animations do not.'}, 'asset_id': {'type': 'string', 'description': 'asset_id returned by start_lowpoly_generate or get_lowpoly_job.'}, 'animation': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Animation name for the gif, sheet and mp4 targets. Omit it for gif or sheet to get every animation in one zip.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
fix_pixel_art
Fix Pixel Art
Recover the native pixel grid from enlarged, softened, AI-rendered, or compressed pixel art.
Standard uses the native Rust detector. Neural uses the neural reconstruction engine and
accepts optional target width and height values. This repairs existing artâit does not generate
a new image. Both engines are free and share a limit of 10 requests per minute per API token.
Provide exactly one source as base64 input_image or a public HTTPS image_url. URL input avoids
the ALB request-body limit. Decoded images may contain up to 16 megapixels. Successful response
JSON is limited to 850,000 bytes for AWS ALB compatibility.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'properties': {'width': {'anyOf': [{'type': 'integer', 'exclusiveMinimum': 0}, {'type': 'null'}], 'default': None, 'description': "Optional neural target dimension in pixels. Accepted only with engine='neural'."}, 'engine': {'enum': ['standard', 'neural'], 'type': 'string', 'default': 'standard', 'description': 'Fixer engine. Standard uses the native Rust detector; neural uses the neural reconstruction engine.'}, 'height': {'anyOf': [{'type': 'integer', 'exclusiveMinimum': 0}, {'type': 'null'}], 'default': None, 'description': "Optional neural target dimension in pixels. Accepted only with engine='neural'."}, 'image_url': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Public HTTPS PNG or JPEG URL to reconstruct. Provide this or input_image, not both. URL downloads may contain up to 20 MB and bypass the API request-body limit.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}, 'input_image': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Base64 PNG or JPEG to reconstruct at its native pixel grid. Raw base64 or a data URL; provide this or image_url, not both. Decoded input may contain up to 16 megapixels, and complete base64 request JSON must stay within 900,000 bytes.'}, 'timeout_seconds': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': 'Read-timeout override in seconds for this call; increase for animations or large batches.'}}}
Output schema
{'type': 'object', 'additionalProperties': {'type': 'array', 'items': {'type': 'string'}}}
get_balance
Get Balance
Get credits/balance using the public /v2/inferences/credits endpoint.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'properties': {'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
get_inference_job
Check Async Job
Check the status of an async generation started with start_inference_job.
Statuses: pending, running, succeeded, failed. On success the result carries hosted
output_urls (raw base64 payloads are excluded to keep MCP outputs compact).
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['task_id'], 'properties': {'task_id': {'type': 'string', 'description': 'Async job id returned by start_inference_job.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
get_inference_result
Get Generated Outputs
Retrieve retained outputs for a synchronous generation.
Use the request_id returned by create_inference to recover or refresh signed output URLs.
This lookup is read-only; never repeat a paid create_inference call just because delivery URLs
are temporarily missing.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['request_id'], 'properties': {'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}, 'request_id': {'type': 'string', 'description': 'Inference request id returned by create_inference.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
get_lowpoly_job
Check Low-Poly Job
Status of a Low-Poly job: pending, running, succeeded or failed. On success, the model with its versions,
render URLs and animations. Poll every 10-20 seconds; jobs take minutes.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['task_id'], 'properties': {'task_id': {'type': 'string', 'description': 'Async job id returned by start_inference_job.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
get_lowpoly_model
Get Low-Poly Model
A Low-Poly model: status, versions (render URLs, animations) and any running job.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['asset_id'], 'properties': {'asset_id': {'type': 'string', 'description': 'asset_id returned by start_lowpoly_generate or get_lowpoly_job.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
get_lowpoly_pricing
Low-Poly Pricing
Low-Poly (3D) sizes, prices per operation (generate / revise / animate), styles, limits and export targets. Free.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'properties': {'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
get_service_status
Service Status
Check RetroDiffusion subsystem health (/v2/status, no auth). Useful before bulk generation runs.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'properties': {}}
Output schema
{'type': 'object', 'additionalProperties': True}
get_style_usage
Get Style Usage
Explain how to use a public prompt_style from the RetroDiffusion API.
Use this before create_inference if you are unsure whether a style expects `input_image`,
supports per-inference `reference_images`, or whether you meant style-level `style_reference_images`.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['prompt_style'], 'properties': {'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}, 'prompt_style': {'type': 'string', 'description': "Style id from list_available_styles (e.g. 'rd_fast__default', 'rd_pro__isometric', or a custom 'user__...' style)."}}}
Output schema
{'type': 'object', 'additionalProperties': True}
list_available_models
List Models
Return unique public model identifiers available in /v2/styles/selector.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'properties': {'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
list_available_styles
List Styles
List publicly available styles from /v2/styles/selector.
Use this to discover valid prompt_style values plus style metadata such as require_input_image and supports_reference_images.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'properties': {'tab': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Filter styles by tab: tab:image, tab:animation, tab:advanced-animation, or tab:tileset.'}, 'model': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Filter styles by model: rd_fast, rd_plus, rd_pro, or rd_mini.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
list_edit_tools
List Edit Tools
List the enabled canvas edit tools from /v2/edit/tools with their fields, costs, and limits.
Edit tools are the recommended way to post-process generated pixel art: background removal,
palette conversion, color reduction, pixel correction, rotation, inpainting, outpainting,
seam tiling, and prompt-driven edits.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'properties': {'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
list_inference_jobs
List Async Jobs
List your most recent async jobs, newest first (GET /v2/inferences/tasks).
Recovery path: if a submission response was lost (timeout, disconnect) before the
task_id arrived, the job was still accepted â find it here instead of re-submitting
and being charged twice. Then poll it with get_inference_job.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'properties': {'limit': {'type': 'integer', 'default': 20, 'maximum': 100, 'minimum': 1, 'description': 'Maximum number of recent jobs to return (1-100, default 20).'}, 'status': {'anyOf': [{'enum': ['pending', 'running', 'succeeded', 'failed'], 'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Optional: only return jobs with this status.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
list_lowpoly_models
List Low-Poly Models
The account's Low-Poly models, newest first.
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'properties': {'limit': {'type': 'integer', 'default': 20, 'maximum': 100, 'minimum': 1, 'description': 'How many models to return (newest first).'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
logout
Log Out
Clear the authenticated RetroDiffusion API key for this MCP session.
Idempotent
Input schema
{'type': 'object', 'properties': {}}
Output schema
{'type': 'object', 'additionalProperties': True}
recolor_lowpoly_model
Recolor Low-Poly Model
Recolor a Low-Poly model's textures with the image color tools and save the result as a new version
(returns the model). Color Reducer and Palette Converter are free; Color Style Transfer costs $0.01.
Later revisions and animations keep the new colors.
Open world
Input schema
{'type': 'object', 'required': ['asset_id', 'tool'], 'properties': {'tool': {'type': 'string', 'description': "color_reducer (limit the colors), palette_converter (convert to a palette image) or color_style_transfer (take a reference image's color style)."}, 'version': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Version number to work on (default: the newest). Revisions create versions; animations do not.'}, 'asset_id': {'type': 'string', 'description': 'asset_id returned by start_lowpoly_generate or get_lowpoly_job.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}, 'color_count': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'color_reducer: how many colors, 2-256 (omit for automatic).'}, 'dither_mode': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'none | bayer_2x2 | bayer_4x4 | bayer_8x8 (color_reducer, palette_converter).'}, 'palette_image': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Base64 image of a color palette; output colors are constrained to it.'}, 'dither_strength': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': 'Dithering strength, 0-10 (default 5).'}, 'reference_image': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'color_style_transfer: base64 reference image.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
run_edit_tool
Run Edit Tool
Run a canvas edit tool on an image via /v2/edit/tools/{tool_id}.
Free tools: color_reducer, palette_converter, pixel_correction, k_centroid_downscale, rotate.
$0.01 tools: background_remover, color_style_transfer. Premium ($0.18): image_edit, inpainting,
outpainting, seam_tiling. Use estimate_edit_tool_cost first for anything that charges â
estimation is free. The edited image is returned in base64_images.
Open world
Input schema
{'type': 'object', 'required': ['tool_id', 'input_image'], 'properties': {'seed': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Seed for reproducible results; reuse the same seed to iterate on one composition.'}, 'width': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'k_centroid_downscale: target width in pixels (required for that tool).'}, 'height': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'k_centroid_downscale: target height in pixels (required for that tool).'}, 'prompt': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'What to generate or change (required by image_edit and inpainting; optional for outpainting).'}, 'tile_x': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'seam_tiling: repair the horizontal seam (tool default applies when omitted).'}, 'tile_y': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'seam_tiling: repair the vertical seam (tool default applies when omitted).'}, 'tool_id': {'type': 'string', 'description': 'Edit tool id. One of: image_edit, inpainting, outpainting, seam_tiling, background_remover, color_style_transfer, color_reducer, palette_converter, pixel_correction, k_centroid_downscale, rotate. Use list_edit_tools for authoritative fields, costs, and limits.'}, 'expand_top': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Outpainting: pixels to add on the top edge.'}, 'mask_image': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Base64 mask for inpainting: white pixels are regenerated, black pixels are kept.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}, 'seam_width': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'seam_tiling: width in pixels of the seam band to repair.'}, 'color_count': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'color_reducer: target number of colors.'}, 'dither_mode': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'color_reducer/palette_converter: dithering mode.'}, 'expand_left': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Outpainting: pixels to add on the left edge.'}, 'input_image': {'type': 'string', 'description': 'Base64 PNG of the image to edit (raw base64 or a data URL). Required by every edit tool.'}, 'expand_right': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Outpainting: pixels to add on the right edge.'}, 'soft_inpaint': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Inpainting/outpainting: blend edits softly with the surrounding pixels.'}, 'expand_bottom': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Outpainting: pixels to add on the bottom edge.'}, 'input_palette': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Base64 image of a color palette; output colors are constrained to it.'}, 'dither_strength': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': 'color_reducer/palette_converter: dithering strength, 0-10 (0 disables, default 5).'}, 'timeout_seconds': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': 'Read-timeout override in seconds for this call; increase for animations or large batches.'}, 'rotation_degrees': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': 'rotate: rotation angle in degrees (clean-edge pixel rotation).'}, 'extra_input_image': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced).'}, 'force_solid_pixels': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'background_remover: force fully solid or fully transparent pixels (tool default applies when omitted).'}, 'repair_window_size': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'seam_tiling: size of the repair window.'}, 'transparency_threshold': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'background_remover: alpha threshold for treating pixels as transparent.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
start_inference_job
Start Async Generation
Start a generation as an async job (POST /v2/inferences with async=true) and return a task_id.
Recommended for advanced animations (rd_advanced_animation__*), other animation styles, and
batches â they run for tens of seconds and can outlive a synchronous MCP call. Poll the
returned task_id with get_inference_job roughly every 2-5 seconds.
Open world
Input schema
{'type': 'object', 'required': ['prompt', 'prompt_style', 'width', 'height'], 'properties': {'seed': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Seed for reproducible results; reuse the same seed to iterate on one composition.'}, 'width': {'type': 'integer', 'description': "Output width in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage. Genre-native sizes per item: Minecraft 16; items/icons/props 32-64; character sprites 16-48 retro or 96-128 showcase; tiles 16-32; portraits 96-128; full scenes 256 (RD Pro's max; 16:9 scenes = 256x144 â\x80\x94 pixel art integer-upscales losslessly)."}, 'height': {'type': 'integer', 'description': 'Output height in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.'}, 'prompt': {'type': 'string', 'description': "Describe the SUBJECT only, richly and concretely ('a squat round flask of glowing crimson liquid, cork stopper, bright highlight on the upper-left rim' beats 'a potion'). Never write 'pixel art' â\x80\x94 the selected style handles all rendering. For standalone assets, state a flat background color that contrasts the subject (default 'on a plain white background') and pair with remove_bg=true; never write 'transparent background' (that is remove_bg's job), and never leave the background unstated (it drifts to drab dark gray). Scenes instead describe their real environment. For rd_advanced_animation__rotate the prompt is only an optional hint describing the uploaded subject â\x80\x94 a few words or an empty string."}, 'tile_x': {'type': 'boolean', 'default': False, 'description': 'Make the result tile seamlessly on the horizontal axis.'}, 'tile_y': {'type': 'boolean', 'default': False, 'description': 'Make the result tile seamlessly on the vertical axis.'}, 'strength': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': 'How strongly to change input_image, 0-1 (default 0.75). Lower values keep more of the original.'}, 'remove_bg': {'type': 'boolean', 'default': False, 'description': "Remove the background for transparent output. Use true for standalone assets and pair it with a stated contrasting background in the prompt ('on a plain white background') â\x80\x94 removal works best on flat contrasting backdrops. Animations inherit the start frame's transparency automatically."}, 'num_images': {'type': 'integer', 'default': 1, 'description': 'How many images to generate in one batch; a batch produces varied takes of one prompt (the right way to get N distinct items as individually usable images â\x80\x94 never pack N items into a single sheet/grid image unless a sheet IS the deliverable). Style-specific maximums apply.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}, 'input_image': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': "Base64 PNG used as the main source image for edits, variations, tilesets, animations, or styles that require a starting frame. Raw base64 or a data URL. Send the NATIVE-resolution image: an upscaled display copy (e.g. a 96px sprite exported at 4x = 384px) exceeds style ranges and gets rejected â\x80\x94 downscale to the true pixel grid first. For advanced animations the frame's dimensions must equal width/height, and sprites whose opaque pixels touch the canvas edge animate badly (pad onto a larger transparent canvas first, e.g. 48x48 content onto 64x64)."}, 'extra_prompt': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Secondary prompt for styles that use one (e.g. the transition texture in advanced tilesets).'}, 'prompt_style': {'type': 'string', 'description': "Style id from list_available_styles (e.g. 'rd_fast__default', 'rd_pro__isometric', or a custom 'user__...' style)."}, 'input_palette': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Base64 image of a color palette; output colors are constrained to it.'}, 'upload_outputs': {'type': 'boolean', 'default': True, 'description': 'Host outputs and return URLs in output_urls (recommended for MCP clients) instead of only base64 payloads.'}, 'frames_duration': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Animation frame count for animation styles: 4, 6, 8, 10, 12, or 16. Pick deliberately: 8 is the sweet spot for loops (walking, idle), 6 for a snappy single action, 10-12 for flowing ambient motion. Ignored by rd_advanced_animation__rotate (always 8 views).'}, 'timeout_seconds': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': 'Read-timeout override in seconds for this call; increase for animations or large batches.'}, 'reference_images': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'default': None, 'description': 'Extra per-inference guidance images (base64), only for styles where supports_reference_images is true. Not for defining custom styles.'}, 'extra_input_image': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced).'}, 'return_pre_palette': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Also return the render from before palette constraints were applied.'}, 'return_spritesheet': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'For animation styles: return a PNG sprite sheet instead of a GIF (for rd_advanced_animation__rotate, the 3x3 direction sheet whose views face the center).'}, 'return_non_bg_removed': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Also return the render from before background removal was applied.'}, 'upscale_output_factor': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Integer upscale factor for the output image; 1 returns the native pixel size.'}, 'bypass_prompt_expansion': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Skip the automatic LLM prompt enrichment and use the prompt verbatim.'}, 'include_downloadable_data': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Include extra structured assets when available (e.g. tileset atlas JSON, animation frame data).'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
start_lowpoly_animate
Start Low-Poly Animation
Add an animation to a Low-Poly model version, or change an existing one by passing its name as animation
(paid, priced by size). The first animation rigs the model for free. Animations attach to the version; they do
not create a new version. Poll get_lowpoly_job(task_id).
Open world
Input schema
{'type': 'object', 'required': ['asset_id', 'prompt'], 'properties': {'mode': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Omit (auto) to let the service pick: quality, or fast for simple requests. "quality" or "fast" to choose. Same price.'}, 'prompt': {'type': 'string', 'description': "The motion, e.g. 'a bouncy walk cycle' or 'swing the sword overhead'. With animation: what should change about it."}, 'version': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Version number to work on (default: the newest). Revisions create versions; animations do not.'}, 'asset_id': {'type': 'string', 'description': 'asset_id returned by start_lowpoly_generate or get_lowpoly_job.'}, 'animation': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Name of an existing animation on the version to change instead of adding a new one (it keeps its name). Omit to add a new animation.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}, 'idempotency_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Optional retry key: repeating a start call with the same key returns the same job instead of charging again.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
start_lowpoly_generate
Start Low-Poly 3D Model
Start building a low-poly 3D model with pixel-art textures from a prompt and/or reference images (paid).
reference_models puts your existing models (by asset_id) into it exactly, e.g. "a tavern with my table".
Optional input_palette (a palette image, as for create_inference): the model uses only its colors, and
revisions and animations keep them.
Returns task_id and asset_id immediately; poll get_lowpoly_job(task_id) until it succeeds (usually 1-5 minutes).
Then use export_lowpoly_model for .glb/.bbmodel/Minecraft/OBJ files, start_lowpoly_revise to change it, or
start_lowpoly_animate to add motion. Failed jobs are refunded automatically; never restart a running job.
Open world
Input schema
{'type': 'object', 'properties': {'mode': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Omit (auto) to let the service pick: quality, or fast for simple requests. "quality" or "fast" to choose. Same price.'}, 'size': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Cube size in texels: "16", "32", "64", "128", "256", or "auto" (default). Auto reads the prompt; reference-image-only requests default to 64. Bigger sizes cost more (see get_lowpoly_pricing).'}, 'style': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Low-Poly style id: rd_lowpoly__detailed (default, free-form shapes), rd_lowpoly__blocky (boxes only, tilted where needed, Minecraft-like), their Lite versions rd_lowpoly__detailed_lite / rd_lowpoly__blocky_lite (a lighter model: simpler results for much less, and Lite prices for everything done to the model later), or another style listed by get_lowpoly_pricing (each style lists its prices).'}, 'prompt': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'What to build or change, up to 250 characters.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}, 'input_palette': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Base64 image of a color palette; output colors are constrained to it.'}, 'idempotency_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Optional retry key: repeating a start call with the same key returns the same job instead of charging again.'}, 'reference_images': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'default': None, 'description': 'Up to 4 base64 reference images (PNG/JPEG/WEBP) of the object, e.g. front and side views.'}, 'reference_models': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'default': None, 'description': 'asset_ids of your own finished Low-Poly models to build in: each is placed exactly (same shapes and textures) where the prompt puts it, or adapted. Images and models together: at most 4.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
start_lowpoly_rerig
Re-rig Low-Poly Model
Rebuild the skeleton of a rigged Low-Poly model version (paid, priced by size), e.g. to move a pivot or add
bones. The version is updated in place; animations whose bones the new rig still has are kept. Versions without
a rig are rigged for free by their first animation instead. Poll get_lowpoly_job(task_id).
Open world
Input schema
{'type': 'object', 'required': ['asset_id'], 'properties': {'prompt': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': "What to change about the rig, e.g. 'give the tail three bones' (up to 250 characters). Omit for a fresh rig."}, 'version': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Version number to work on (default: the newest). Revisions create versions; animations do not.'}, 'asset_id': {'type': 'string', 'description': 'asset_id returned by start_lowpoly_generate or get_lowpoly_job.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}, 'idempotency_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Optional retry key: repeating a start call with the same key returns the same job instead of charging again.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
start_lowpoly_revise
Start Low-Poly Revision
Change an existing Low-Poly model (paid, priced by its size). The result is saved as a new version.
Poll get_lowpoly_job(task_id). One job per model at a time.
Open world
Input schema
{'type': 'object', 'required': ['asset_id', 'prompt'], 'properties': {'mode': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Omit (auto) to let the service pick: quality, or fast for simple requests. "quality" or "fast" to choose. Same price.'}, 'prompt': {'type': 'string', 'description': 'What should change, up to 250 characters.'}, 'version': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Version number to work on (default: the newest). Revisions create versions; animations do not.'}, 'asset_id': {'type': 'string', 'description': 'asset_id returned by start_lowpoly_generate or get_lowpoly_job.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}, 'idempotency_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Optional retry key: repeating a start call with the same key returns the same job instead of charging again.'}, 'reference_images': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'default': None, 'description': 'Up to 4 base64 reference images (PNG/JPEG/WEBP) of the object, e.g. front and side views.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
start_lowpoly_split
Split Low-Poly Model
Break a Low-Poly model into separate models (paid, priced by its size): a desk scene becomes the desk, a
candle, each book, and so on. Each piece is a new model (and history item) facing the front, with its own
textures, rig and animations; the original is unchanged. Poll get_lowpoly_job(task_id); its pieces list the
new models.
Open world
Input schema
{'type': 'object', 'required': ['asset_id'], 'properties': {'prompt': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': "How to split, e.g. 'only the books' or 'each drawer too' (up to 250 characters). Omit to split off every separate object that makes sense."}, 'version': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Version number to work on (default: the newest). Revisions create versions; animations do not.'}, 'asset_id': {'type': 'string', 'description': 'asset_id returned by start_lowpoly_generate or get_lowpoly_job.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}, 'idempotency_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Optional retry key: repeating a start call with the same key returns the same job instead of charging again.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
update_user_style
Update Custom Style
Update a public RD Pro user style using /v2/styles/{style_id}.
Use `style_reference_images` and `style_reference_caption` for style-level references.
These are baked into the custom style and are not the same as per-inference `reference_images`.
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['style_id'], 'properties': {'name': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'New display name for the custom style.'}, 'style_id': {'type': 'string', 'description': 'Style id â\x80\x94 the internal id or the prompt_style/public id (e.g. user__mystyle_ab12).'}, 'min_width': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Force a fixed width (96-256); must be provided together with min_height.'}, 'min_height': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Force a fixed height (96-256); must be provided together with min_width.'}, 'rd_api_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.'}, 'style_icon': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': "Icon name for the style (e.g. 'sparkles')."}, 'description': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Short description of the custom style.'}, 'force_palette': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Always apply palette constraining for this style.'}, 'force_bg_removal': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Always remove backgrounds for this style.'}, 'llm_instructions': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Instructions for the prompt-expansion LLM when this style is used.'}, 'reference_images': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'default': None, 'description': 'Alias for style_reference_images on this tool; prefer style_reference_images and never provide both.'}, 'reference_caption': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Alias for style_reference_caption on this tool; prefer style_reference_caption and never provide both.'}, 'apply_prompt_fixer': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Let the API tidy prompts automatically for this style (default true).'}, 'user_prompt_template': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Prompt template for the style; must contain the {prompt} token.'}, 'style_reference_images': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'default': None, 'description': 'Style-level reference image(s), base64, baked into the custom style (max 1 via the public API).'}, 'reset_forced_dimensions': {'type': 'boolean', 'default': False, 'description': 'Clear previously forced dimensions; do not combine with min_width/min_height.'}, 'style_reference_caption': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Caption describing the style reference image(s).'}, 'expanded_llm_instructions': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Extended instructions for the prompt-expansion LLM.'}}}
Output schema
{'type': 'object', 'additionalProperties': True}
History
Recent tool changes
Changed
start_lowpoly_generate
Sept. 29, 2026, 3 a.m.
Changed
estimate_lowpoly_cost
Sept. 29, 2026, 3 a.m.
Added
delete_lowpoly_animation
Sept. 27, 2026, 2:51 a.m.
Added
recolor_lowpoly_model
Sept. 27, 2026, 2:51 a.m.
Changed
export_lowpoly_model
Sept. 27, 2026, 2:51 a.m.
Added
start_lowpoly_rerig
Sept. 27, 2026, 2:51 a.m.
Added
start_lowpoly_split
Sept. 27, 2026, 2:51 a.m.
Changed
start_lowpoly_animate
Sept. 27, 2026, 2:51 a.m.
Changed
start_lowpoly_revise
Sept. 27, 2026, 2:51 a.m.
Changed
start_lowpoly_generate
Sept. 27, 2026, 2:51 a.m.
Changed
estimate_lowpoly_cost
Sept. 27, 2026, 2:51 a.m.
Added
export_lowpoly_model
Sept. 25, 2026, 3 a.m.
Added
list_lowpoly_models
Sept. 25, 2026, 3 a.m.
Added
get_lowpoly_model
Sept. 25, 2026, 3 a.m.
Added
get_lowpoly_job
Sept. 25, 2026, 3 a.m.
Added
start_lowpoly_animate
Sept. 25, 2026, 3 a.m.
Added
start_lowpoly_revise
Sept. 25, 2026, 3 a.m.
Added
start_lowpoly_generate
Sept. 25, 2026, 3 a.m.
Added
estimate_lowpoly_cost
Sept. 25, 2026, 3 a.m.
Added
get_lowpoly_pricing
Sept. 25, 2026, 3 a.m.
Added
get_service_status
Sept. 17, 2026, 7:57 a.m.
Added
list_inference_jobs
Sept. 17, 2026, 7:57 a.m.
Added
get_inference_job
Sept. 17, 2026, 7:57 a.m.
Added
start_inference_job
Sept. 17, 2026, 7:57 a.m.
Added
get_inference_result
Sept. 17, 2026, 7:57 a.m.
Added
estimate_edit_tool_cost
Sept. 17, 2026, 7:57 a.m.
Added
run_edit_tool
Sept. 17, 2026, 7:57 a.m.
Added
fix_pixel_art
Sept. 17, 2026, 7:57 a.m.
Added
list_edit_tools
Sept. 17, 2026, 7:57 a.m.
Added
create_inference
Sept. 17, 2026, 7:57 a.m.
Discover
Similar MCP servers
GripForge
io.github.gripforgeai/mcp
Generates, rigs, animates, analyzes, and packages game characters, weapons, armor, effects, environments, and engine-ready assets.
spriteship
com.spriteship/spriteship
Generates and manages 2D game characters, assets, animations, tilesets, UI packs, maps, and engine-ready exports for multiple gam…
Ludo AI Game Assets
ai.ludo/game-assets
Generates game assets including sprites, 3D models, animations, sound effects, music, and voice content.
3DAssets.dev
dev.3dassets/catalogue
Searches and delivers free CC0 GLB models and game asset packs, with licensing details, CDN links, scene layouts, and loader usag…
AXIS Avatar Foundry
com.jonathanarvay/axis-avatar-foundry
Generates, repairs, rigs, validates, retargets, compares, and exports production-ready 3D avatars and meshes for game platforms.
Polyfork low-poly 3D assets
dev.polyfork/polyfork
Searches, previews and composes low-poly 3D assets and kits for three.js and game engines, including terrain, variants, scene pre…
Spritesheet Forge
io.github.LAXY9887/spritesheet-forge
Converts, trims, splits, assembles, and animates PNG, GIF, and spritesheet assets for game development.
Portamora
app.portamora/mcp
Allows users to discover published atmospheric 3D worlds, inspect world metadata and guides, and obtain starter materials for bui…