Sourceful

This page is auto-generated from model configurations. Last updated: 2026-03-13.

This reference lists all available Sourceful image generation models and their parameters. Use these parameter names when calling the Generation API.


Riverflow 2.0 Fast

Agentic image model optimized for high-quality, fast generations.

Model ID: model_sourceful-riverflow-2-0-fast

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_sourceful-riverflow-2-0-fast/markdown

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
promptstringYes----Generation instruction
referenceImagesfile_arrayNo----Reference images to edit.
superResolutionRefsfile_arrayNo----Optional reference images for detail fix
resolutionstringNo1K--1K, 2KTarget resolution
aspectRatiostringNoauto--auto, 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16Aspect ratio for output.
fontUrlsstring_arrayNo----Optional font URLs (ttf/otf/woff/woff2). Up to 2.
fontTextsstring_arrayNo----Text strings matching font_urls (≤300 chars each).
transparencybooleanNofalse---Enable transparent background when supported.
enhancePromptbooleanNofalse---Let model enhance the instruction.
maxIterationsnumberNo313-Number of internal reasoning iterations.

Riverflow 2.0 Pro

Agentic image model optimized for robust, high-precision generations supporting font control

Model ID: model_sourceful-riverflow-2-0-pro

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_sourceful-riverflow-2-0-pro/markdown

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
promptstringYes----Generation instruction
referenceImagesfile_arrayNo----Reference images to edit.
superResolutionRefsfile_arrayNo----Optional reference images for detail fix
resolutionstringNo1K--1K, 2K, 4KTarget resolution
aspectRatiostringNoauto--auto, 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16Aspect ratio for output.
fontUrlsstring_arrayNo----Optional font URLs (ttf/otf/woff/woff2). Up to 2.
fontTextsstring_arrayNo----Text strings matching font_urls (≤300 chars each).
transparencybooleanNofalse---Enable transparent background when supported.
enhancePromptbooleanNofalse---Let model enhance the instruction.
maxIterationsnumberNo313-Number of internal reasoning iterations.

Riverflow 2.0 REFSR

Render product images with 100% accuracy and environmental blending

Model ID: model_sourceful-riverflow-2-0-refsr

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_sourceful-riverflow-2-0-refsr/markdown

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
referenceImagefileYes----The base image to apply super resolution to.
superResolutionReferencesfile_arrayYes----Reference images for super resolution guidance.