Reve 2.1 Image Edit API

Reve 2.1 Edit

Reve 2.1 Edit applies natural-language instructions to an existing image. It is designed for precise visual changes, layout-aware recomposition, and detailed image refinement while preserving the parts of the source image that should remain unchanged.

Why Choose This?

Instruction-based image editing
Edit an existing image by describing the desired change in natural language.
Precise visual refinement
Apply focused changes to objects, backgrounds, colors, lighting, layout, or style.
Preservation-aware editing
Keep important parts of the original image unchanged while modifying selected details.
Layout-aware recomposition
Adjust composition and visual structure while maintaining a coherent final image.
Flexible output formats
Export edited images as png, jpeg, or webp.

Parameters

Parameter	Required	Description
prompt	Yes	Text description of how to edit the reference image.
image	Yes	Reference image to edit. Public image URLs and uploaded images are supported.
aspect_ratio	No	Output aspect ratio, including `auto` and supported ratio presets.
output_format	No	Output format: `png`, `jpeg`, or `webp`.

How to Use

Upload your image — Provide the source image you want to edit.
Write your edit prompt — Describe the desired changes and clearly state what should remain unchanged.
Choose aspect ratio — Select an aspect ratio or use auto to let the model choose the best layout.
Choose output format — Select png, jpeg, or webp when needed.
Submit — Generate the edited image and retrieve the output URL.

Pricing

Output	Price
One image	$0.28

Best Use Cases

Background editing — Replace, clean up, or restyle image backgrounds.
Object changes — Remove, replace, recolor, or refine objects in an image.
Product image refinement — Improve product visuals for marketing, ecommerce, and presentation.
Layout adjustments — Recompose images while keeping the main subject and visual intent intact.
Portrait and scene edits — Adjust style, lighting, mood, or environment in existing images.

Pro Tips

Describe both the change and the elements that must stay unchanged.
Use concise, concrete instructions for object removal, replacement, color, lighting, and background edits.
Use a clear source image with the main subject visible.
Use png for high-quality general output, jpeg for smaller files, and webp for web-friendly images.

2.1 Edit API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/reve/2.1/edit with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read URLs from data.outputs. Examples for 2.1 Edit below.

HTTP example

# Submit the prediction
curl --fail-with-body --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/reve/2.1/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",
    "image": "https://example.com/your-input.jpg",
    "aspect_ratio": "4:1",
    "output_format": "jpeg",
    "enable_sync_mode": false,
    "enable_base64_output": false
}'

# Wait at least 2 seconds, then poll. Safe GET requests may be retried.
curl --fail-with-body --connect-timeout 10 --max-time 30 \
  --retry 4 --retry-all-errors --retry-delay 1 \
  -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# Start at 2 seconds and increase the interval for long-running tasks.
# Stop on completed, failed, cancelled, or timeout.

Node.js example

// npm install wavespeed
const { Client } = require('wavespeed');

const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
const client = new Client(apiKey, {
  maxConnectionRetries: 5,
  retryInterval: 1.0,
});

try {
  const result = await client.run("reve/2.1/edit", {
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "image": "https://example.com/your-input.jpg",
        "aspect_ratio": "4:1",
        "output_format": "jpeg",
        "enable_sync_mode": false,
        "enable_base64_output": false
}, {
    timeout: 3600,
    pollInterval: 2.0,
  });
  console.log(result.outputs);
} catch (error) {
  console.error('Generation failed:', error);
  process.exitCode = 1;
}

Python example

# pip install wavespeed
import os
from wavespeed import Client

client = Client(
    api_key=os.environ["WAVESPEED_API_KEY"],
    max_connection_retries=5,
    retry_interval=1.0,
)

try:
    output = client.run(
        "reve/2.1/edit",
        {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "image": "https://example.com/your-input.jpg",
    "aspect_ratio": "4:1",
    "output_format": "jpeg",
    "enable_sync_mode": false,
    "enable_base64_output": false
},
        timeout=3600.0,
        poll_interval=2.0,
    )
    print(output["outputs"])
except Exception as error:
    raise SystemExit(f"Generation failed: {error}") from error

2.1 Edit API — Frequently asked questions

What is the 2.1 Edit API?

2.1 Edit is a Reve model for image editing, exposed as a REST API on WaveSpeedAI. Reve 2.1 Image Edit transforms existing images with natural-language edit instructions, preserving layout intelligence, accurate text rendering, and fine visual details for posters, ads, product visuals, and typography-rich designs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the 2.1 Edit API?

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 result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/reve/reve-2.1-edit.

How much does 2.1 Edit cost per run?

2.1 Edit starts at $0.28 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.

What inputs does 2.1 Edit accept?

Key inputs: `prompt`, `image`, `aspect_ratio`, `enable_base64_output`, `enable_sync_mode`, `output_format`. 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/reve/reve-2.1-edit.

How do I get started with the 2.1 Edit API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use 2.1 Edit outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Reve). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

EsempiVedi tutto

Modelli correlati

README