Reve 2.1 Image Remix API

Reve 2.1 Remix

Reve 2.1 Remix creates a new image from one or more reference images and a text prompt. It is designed for multi-reference composition, style transfer, subject blending, and controlled visual remixing across creative and production workflows.

Why Choose This?

Multi-reference image remixing
Combine one or more reference images into a new generated image.
Prompt-guided composition
Describe how the references should be combined, transformed, or reinterpreted.
Flexible creative control
Blend subjects, styles, layouts, and visual elements into a new composition.
Reference-aware generation
Use image position tags in the prompt when you need to assign a specific role to a specific reference image.
Flexible output formats
Export remixed images as png, jpeg, or webp.

Parameters

Parameter	Required	Description
prompt	Yes	Instructions for combining or transforming the reference images.
images	Yes	Refer to them in the prompt with zero-based frame tags.
aspect_ratio	No	Output aspect ratio, including several supported ratio presets.
output_format	No	Output format: `png`, `jpeg`, or `webp`.

How to Use

Upload reference images — Provide one to eight images for the remix.
Write your prompt — Describe the desired composition and how the references should be used.
Choose aspect ratio — Select an aspect ratio to let the model choose the best layout.
Choose output format — Select png, jpeg, or webp.
Submit — Generate the remixed image and retrieve the output URL.

Pricing

Output	Price
One image	$0.28

Best Use Cases

Multi-reference creative composition — Combine multiple visual sources into a new image.
Style exploration — Transfer or blend visual direction from one or more references.
Product and campaign concepting — Build concept images from product, branding, or lifestyle references.
Character and subject blending — Mix subjects, outfits, scenes, or visual identities into a new composition.
Creative development — Explore new visual directions from a controlled set of references.

Pro Tips

Keep each reference image clear and relevant to the requested composition.
Explicitly describe how each frame should contribute to the result.
Use frame tags when the prompt refers to a specific reference image.
Keep the composition request focused when using many reference images.
Use png for high-quality general output, jpeg for smaller files, and webp for web-friendly images.

2.1 Remix API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/reve/2.1/remix 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 Remix 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/remix" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "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/remix", {
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "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/remix",
        {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "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 Remix API — Frequently asked questions

What is the 2.1 Remix API?

2.1 Remix is a Reve model for image editing, exposed as a REST API on WaveSpeedAI. Reve 2.1 Image Remix combines one or more reference images with a text prompt to create new image compositions, blending visual references while preserving layout intelligence, visual consistency, and fine image details for posters, ads, product visuals, and creative design workflows. 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 Remix 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-remix.

How much does 2.1 Remix cost per run?

2.1 Remix 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 Remix accept?

Key inputs: `prompt`, `images`, `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-remix.

How do I get started with the 2.1 Remix 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 Remix 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.

ExemplosVer todos

Modelos relacionados

README