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.
Idle

$0.135per run·~74 / $10

Change to a natural, realistic style, the woman depicted in Figure 1 is now wearing the coat from Figure 2 — a detailed, well-fitted garment with visible texture, stitching, and realistic fabric folds. The coat’s design, color, and material should match the original image precisely, with no alterations to its structure or appearance. The woman’s posture, expression, and surroundings remain unchanged, ensuring the transformation is seamless and visually coherent. The lighting, background, and overall environment should stay consistent with the original scene to preserve narrative continuity. This is a natural, high-resolution, photorealistic rendering.

Style: Artistic colorization with emphasis on mood, composition, and visual harmony. The image should be rendered in a rich, cinematic palette—vibrant yet balanced—where colors enhance emotional tone rather than overpower it. Use selective saturation to highlight key elements while preserving natural textures and depth. Employ a painterly or filmic aesthetic, with soft gradients and atmospheric lighting to evoke a specific mood (e.g., nostalgic, surreal, melancholic, or vibrant). Avoid flat or overly saturated tones; prioritize artistic integrity and visual storytelling. The final output should feel emotionally resonant, visually immersive, and stylistically cohesive.
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.
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.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text instruction describing the desired edit |
| images | Yes | Reference images (1-10, click "+ Add Item" for multiple) |
| resolution | No | Output resolution: 1k (default), 2k, 4k |
| aspect_ratio | No | Output ratio: auto (default), 1:1, 21:9, 16:9, 3:2, 4:3, 5:4, 4:5, 3:4, 2:3, 9:16 |
| transparency | No | Enable transparent background (default: disabled) |
| Resolution | Cost per image |
|---|---|
| 1K | $0.135 |
| 2K | $0.135 |
| 4K | $0.297 |
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/sourceful/riverflow-2.0-pro/edit with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Riverflow 2.0 Pro Edit below.
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/sourceful/riverflow-2.0-pro/edit" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"resolution": "1k",
"aspect_ratio": "auto",
"transparency": false
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("sourceful/riverflow-2.0-pro/edit", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"resolution": "1k",
"aspect_ratio": "auto",
"transparency": false
});
console.log(result.outputs[0]); // → URL of the generated output# pip install wavespeed
import wavespeed
output = wavespeed.run(
"sourceful/riverflow-2.0-pro/edit",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"resolution": "1k",
"aspect_ratio": "auto",
"transparency": false
}
)
print(output["outputs"][0]) # → URL of the generated outputRiverflow 2.0 Pro Edit is a Sourceful model for image editing, exposed as a REST API 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. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/sourceful/sourceful-riverflow-2.0-pro-edit.
Riverflow 2.0 Pro Edit starts at $0.14 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `prompt`, `images`, `aspect_ratio`, `resolution`, `transparency`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/sourceful/sourceful-riverflow-2.0-pro-edit.
Average end-to-end generation time on WaveSpeedAI is around 130 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (Sourceful). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.