Retro-Diffusion
This page is auto-generated from model configurations. Last updated: 2026-03-13.
This reference lists all available Retro-Diffusion image generation models and their parameters. Use these parameter names when calling the Generation API.
Retro Diffusion Animation
A dedicated animation model featuring specialized motion-aware generation, perfect for sprite sequences.
Model ID: model_retrodiffusion-animation
Capabilities: txt2img
LLM Markdown: https://app.scenario.com/api/models/model_retrodiffusion-animation/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt | string | Yes | - | - | - | - | Text prompt for generation |
image | file | No | - | - | - | - | Input image for image-to-image generation or reference. Will be converted to RGB without transparency. |
style | string | No | four_angle_walking | - | - | four_angle_walking, walking_and_idle, small_sprites, vfx | Style to apply to the generated image |
width | number | No | 48 | 24 | 96 | - | Animation width. four_angle_walking and walking_and_idle only support 48. small_sprites only supports 32. vfx supports 24-96. |
height | number | No | 48 | 24 | 96 | - | Animation height. four_angle_walking and walking_and_idle only support 48. small_sprites only supports 32. vfx supports 24-96. |
returnSpritesheet | boolean | No | false | - | - | - | Return animation as a spritesheet PNG instead of animated GIF |
bypassPromptExpansion | boolean | No | false | - | - | - | Disable automatic prompt expansion |
seed | number | No | - | - | - | - | Random seed. Set for reproducible generation |
Retro Diffusion Plus
A premium pixel-art generation model designed for exceptional quality, rich detail, and stylistic accuracy.
Model ID: model_retrodiffusion-plus
Capabilities: txt2img
LLM Markdown: https://app.scenario.com/api/models/model_retrodiffusion-plus/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt | string | Yes | - | - | - | - | Text prompt for generation |
style | string | No | default | - | - | default, retro, watercolor, textured, cartoon, ui_element, item_sheet, character_turnaround, environment, isometric, isometric_asset, topdown_map, topdown_asset, classic, topdown_item, low_res, mc_item, mc_texture, skill_icon | Style to apply to the generated image |
image | file | No | - | - | - | - | Input image for image-to-image generation or reference. Will be converted to RGB without transparency. |
strength | number | No | 0.8 | 0 | 1 | - | Prompt strength in image-to-image generation. Higher values give closer adherence to the prompt, and lower values use more information from the input image. Only used when Reference Image is provided. |
inputPalette | file | No | - | - | - | - | Reference palette image to guide color choices |
width | number | No | 256 | 16 | 384 | - | Image width |
height | number | No | 256 | 16 | 384 | - | Image height |
numOutputs | number | No | 1 | 1 | 10 | - | Number of images to generate |
removeBg | boolean | No | false | - | - | - | Remove background to create transparent images |
tileX | boolean | No | false | - | - | - | Enable seamless tiling on X axis |
tileY | boolean | No | false | - | - | - | Enable seamless tiling on Y axis |
bypassPromptExpansion | boolean | No | false | - | - | - | Disable automatic prompt expansion |
seed | number | No | - | - | - | - | Random seed. Set for reproducible generation |
Retro Diffusion Tile
A specialized model built for generating seamless, top-down tilemaps with perfect grid alignment and terrain coherence.
Model ID: model_retrodiffusion-tile
Capabilities: txt2img
LLM Markdown: https://app.scenario.com/api/models/model_retrodiffusion-tile/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt | string | Yes | - | - | - | - | Text prompt for generation |
image | file | No | - | - | - | - | Reference image for image-to-image generation or reference. Will be converted to RGB without transparency. |
style | string | No | tileset | - | - | tileset, tileset_advanced, single_tile, tile_variation, tile_object, scene_object | Style to apply to the generated image tileset: Create full tilesets from a simple prompt describing the textures or environment, using a simple set of "wang" style combinations tileset_advanced: Full tilesets from two prompts and/or textures, using a simple set of "wang" style combinations single_tile: Detailed single tile texture for creating full tilesets or surfaces tile_variation: Texture variations of the provided tile image tile_object: Small assets for placing on sections of tiles scene_object: Large assets for placing on tileset maps |
width | number | No | 32 | 16 | 384 | - | Tile width (for tilesets, this is the size of each individual tile, not the output image) |
height | number | No | 32 | 16 | 384 | - | Tile height (for tilesets, this is the size of each individual tile, not the output image) |
numOutputs | number | No | 1 | 1 | 10 | - | Number of images to generate |
bypassPromptExpansion | boolean | No | false | - | - | - | Disable automatic prompt expansion |
seed | number | No | - | - | - | - | Random seed. Set for reproducible generation |
extraImage | file | No | - | - | - | - | Extra reference image for advanced tileset generation |
extraPrompt | string | No | - | - | - | - | Extra prompt for advanced tileset generation |
Updated about 4 hours ago