Browse ModelsSourcefulSourceful Riverflow 2.0 Pro Edit

Sourceful Riverflow 2.0 Pro Edit

Sourceful Riverflow 2.0 Pro Edit

Playground

Try it on WavespeedAI!

Sourceful Riverflow 2.0 Pro Edit is an agentic image model optimized for robust, high-precision image editing and transformation. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

Riverflow 2.0 Pro Edit

Riverflow 2.0 Pro Edit is a premium image editing model that transforms existing images based on text instructions. Upload up to 10 reference images and describe your edits — the model intelligently combines and modifies elements with photorealistic quality at resolutions up to 4K.


Why Choose This?

  • Multi-image reference Support up to 10 reference images for complex editing and element combination.

  • Ultra-high resolution Output at 1K, 2K, or 4K for professional-grade results.

  • Flexible aspect ratios Auto-detect from source or choose from 10 preset options.

  • Transparent background Optional transparency support for compositing workflows.

  • Prompt Enhancer Built-in tool to automatically improve your editing instructions.


Parameters

ParameterRequiredDescription
promptYesText instruction describing the desired edit
imagesYesReference images (1-10, click ”+ Add Item” for multiple)
resolutionNoOutput resolution: 1k (default), 2k, 4k
aspect_ratioNoOutput ratio: auto (default), 1:1, 21:9, 16:9, 3:2, 4:3, 5:4, 4:5, 3:4, 2:3, 9:16
transparencyNoEnable transparent background (default: disabled)

How to Use

  1. Upload your images — add 1-10 reference images by clicking ”+ Add Item”.
  2. Write your prompt — describe the edit, referencing figures by number (e.g., “Figure 1”, “Figure 2”).
  3. Select resolution — 1K for speed, 2K for balanced quality, 4K for maximum detail.
  4. Choose aspect ratio — use auto to match source or pick a specific ratio.
  5. Enable transparency (optional) — check if you need a transparent background.
  6. Run — submit and download your edited image.

Pricing

ResolutionCost per image
1K$0.135
2K$0.135
4K$0.297

Best Use Cases

  • Virtual Try-On — Place clothing or accessories from one image onto a person in another.
  • Element Combination — Merge subjects, objects, or backgrounds from multiple images.
  • Product Visualization — Edit product images with style and context changes.
  • Creative Compositing — Combine elements from multiple references into a cohesive scene.
  • Design Iteration — Rapidly explore variations using multiple reference images.

Pro Tips

  • Reference images by figure number in your prompt (e.g., “the woman in Figure 1 wearing the coat from Figure 2”).
  • Use auto aspect ratio to preserve the original image proportions.
  • 1K and 2K share the same price — choose 2K for better quality at no extra cost.
  • Enable transparency when creating assets for layered designs.
  • Be specific about what to keep, change, and combine for best results.
  • Use high-quality reference images for more precise edits.

Notes

  • Both prompt and images are required fields.
  • Maximum 10 reference images per edit.
  • Ensure uploaded image URLs are publicly accessible.
  • 4K images take longer to generate but provide maximum detail.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/sourceful/riverflow-2.0-pro/edit" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "resolution": "1k",
    "aspect_ratio": "auto",
    "transparency": false
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-Text description of the edits you want to make to the source images.
imagesarrayYes[]1 ~ 10 itemsSource images for editing (1-10 images required).
resolutionstringNo1k1k, 2k, 4kOutput image resolution. Higher resolution produces more detailed images but costs more.
aspect_ratiostringNoautoauto, 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16Aspect ratio of the output image. Use 'auto' to preserve source aspect ratio.
transparencybooleanNofalse-Enable transparent background when supported by the edited content.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction, the ID of the prediction to get
data.modelstringModel ID used for the prediction
data.outputsstringArray of URLs to the generated content (empty when status is not completed).
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2025 WaveSpeedAI. All rights reserved.