# Wan 2.7

> Alibaba's Wan 2.7 image generation and editing model for text-to-image, reference-guided generation, and instruction-based image edits

## Quick Reference

- Model ID: wan-2.7
- Creator: Alibaba
- Status: active
- Family: wan
- Base URL: https://api.lumenfall.ai/openai/v1

## Specifications

- Max Resolution: 2048x2048
- Max Output Images: 4
- Max Input Images: 9
- Input Modalities: text, image
- Output Modalities: image
- Supported Modes: Text to Image, Image Edit

## API Parameters

The compiled parameter schema for this model is available via the API: `GET /v1/models/wan-2.7?schema=true`.

### Core Parameters

- `prompt` (string) — REQUIRED: Text prompt for image generation. Modes: Text to Image, Image Edit
- `seed` (integer): Random seed for reproducibility. Modes: Text to Image, Image Edit

### Size & Layout

- `size` (string): Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9"). Modes: Text to Image, Image Edit
- `aspect_ratio` (string): Aspect ratio of the output image (e.g. "16:9", "1:1"). Modes: Text to Image, Image Edit
- `resolution` (string): Output resolution tier (e.g. "1K", "4K"). Modes: Text to Image, Image Edit

### Media Inputs

- `image` (file) — REQUIRED: Input image(s) to edit. Modes: Image Edit

### Output & Format

- `response_format` (string): How to return the image. Default: url. Values: url, b64_json. Modes: Text to Image, Image Edit
- `output_format` (string): Output image format. Values: png, jpeg, gif, webp, avif. Modes: Text to Image, Image Edit
- `output_compression` (integer): Compression level for lossy formats (JPEG, WebP, AVIF). Modes: Text to Image, Image Edit
- `n` (integer): Number of images to generate. Default: 1. Modes: Text to Image, Image Edit

### Additional Parameters

- `thinking` (string): Model's internal reasoning effort (off, on, minimal, high). Values: off, on. Modes: Text to Image, Image Edit
- `bbox_list` (array): Selected edit regions, aligned to the input image list. Each image supports up to two bounding boxes in [x1, y1, x2, y2] pixel coordinates.. Modes: Text to Image, Image Edit. Only available via alibaba
- `color_palette` (array): Optional custom color theme, available only when image-set mode is disabled.. Modes: Text to Image, Image Edit. Only available via alibaba
- `enable_sequential` (boolean): Whether to enable image-set output mode.. Modes: Text to Image, Image Edit. Only available via alibaba
- `watermark` (boolean): Whether to add the provider watermark to the generated media.. Modes: Text to Image, Image Edit. Only available via alibaba


## Model Identifiers

- Primary Slug: wan-2.7
- Aliases: wan2.7-image

## Dates

- Released: April 2026

## Tags

image-generation, text-to-image, image-editing, multi-image

## Available Providers

### Alibaba Cloud

- Config Key: alibaba/wan-2.7-image
- Provider Model ID: wan2.7-image
- Pricing: $0.030/image


## Performance Metrics

Provider performance over the last 30 days.

### alibaba

- Median Generation Time (p50): 12086ms
- 95th Percentile Generation Time (p95): 27249ms
- Average Generation Time: 14118ms
- Success Rate: 91.3%
- Total Requests: 23
- Time to First Byte (p50): 10161ms
- Time to First Byte (p95): 24060ms


## Arena Benchmarks

### The Capybara Taxi Driver

- Elo: 1127
- Record: 5W / 9L / 3T (17 battles)
- Rank: #17 of 69

### The Reversed Rodeo

- Elo: 1082
- Record: 4W / 5L / 4T (13 battles)
- Rank: #25 of 68

### Chalkboard Menu

- Elo: 1074
- Record: 1W / 8L / 1T (10 battles)
- Rank: #37 of 69

### Outfit Transfer Challenge

- Elo: 1066
- Record: 2W / 4L / 1T (7 battles)
- Rank: #18 of 33


## Use Cases & Category Performance

### Photorealism (Text-to-Image)

- Rank: #36 of 62
- Elo: 1172
- Record: 16W / 26L / 9T (51 battles)
- Win Rate: 31.4%

### Aesthetics (Text-to-Image)

- Rank: #36 of 62
- Elo: 1210
- Record: 17W / 19L / 8T (44 battles)
- Win Rate: 38.6%

### Preservation (Image Editing)

- Rank: #20 of 33
- Elo: 1167
- Record: 6W / 6L / 2T (14 battles)
- Win Rate: 42.9%

### Lighting, Shadows & Materials (Image Editing)

- Rank: #19 of 30
- Elo: 1183
- Record: 5W / 6L / 1T (12 battles)
- Win Rate: 41.7%

### Creativity (Text-to-Image)

- Rank: #42 of 62
- Elo: 1170
- Record: 7W / 7L / 4T (18 battles)
- Win Rate: 38.9%

### Prompt Adherence (Text-to-Image)

- Rank: #42 of 61
- Elo: 1201
- Record: 14W / 25L / 9T (48 battles)
- Win Rate: 29.2%

### Photorealism (Image Editing)

- Rank: #21 of 29
- Elo: 1170
- Record: 5W / 5L / 1T (11 battles)
- Win Rate: 45.5%

### Art (Text-to-Image)

- Rank: #25 of 31
- Elo: 1113
- Record: 5W / 6L / 4T (15 battles)
- Win Rate: 33.3%

### Adding & Editing Objects (Image Editing)

- Rank: #20 of 24
- Elo: 1126
- Record: 3W / 4L / 1T (8 battles)
- Win Rate: 37.5%

### Prompt Adherence (Image Editing)

- Rank: #24 of 26
- Elo: 1128
- Record: 3W / 5L / 2T (10 battles)
- Win Rate: 30.0%

### Product, Branding & Commercial (Text-to-Image)

- Rank: #56 of 61
- Elo: 1121
- Record: 3W / 12L / 1T (16 battles)
- Win Rate: 18.8%

### Text Rendering (Text-to-Image)

- Rank: #59 of 61
- Elo: 1111
- Record: 3W / 12L / 1T (16 battles)
- Win Rate: 18.8%


## Image Gallery

8 images available for this model. Browse all at https://lumenfall.ai/models/alibaba/wan-2.7/gallery

### Curated Examples

- [A wide cinematic shot of a high-end, minimalist boutique storefront at dusk. The shop is built fr...](https://assets.lumenfall.ai/PgIgL4BtaODFfHs53Z2C6ep_2F6YmtDmx-39n4Sga6I/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/ca761u0klb89p3fwioh51inn98d3@jpeg)
- [A meticulous close-up of an elderly artisan's hands carving intricate floral patterns into a bloc...](https://assets.lumenfall.ai/bbY7fLq0dRZc__vfrpw3aj-fqA_Vwunq152XXM18uG4/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/yxik75vh5j2pz4e4u06hddhhiux9@jpeg)
- [A meticulously detailed close-up of an elderly artisan's hands carving an intricate floral patter...](https://assets.lumenfall.ai/4Qy7dzRyr5IkBpj4ajENtLXE8SGAzu5c9-8UYCuJnvk/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/1u55zcrv2d01xcqshf5rxmgo2lsu@jpeg)
- [A sun-drenched artisan bakery storefront with an elegant gold-leaf sign on the window that reads ...](https://assets.lumenfall.ai/k7RiE8Mue0jmtpiLEdr7LPTpaTTAAMV4XncTLznQV8M/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/fddo9b0wmittkl2rbwju2elwepsx@jpeg)

### Arena Competition Results

- [The Capybara Taxi Driver](https://assets.lumenfall.ai/syWBkUiweFbKuanQBha6dvJwCYaiDHnAuLyr8cVJgCM/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/cbxufp62dhpao7ku8fddz5x7rizj@jpeg): #21 of 69 (Elo 1127)
- [Chalkboard Menu](https://assets.lumenfall.ai/UX-Utj1Ge4wmYA1mKeWT1ip6Y8yeql24ZuY_sLUHi6c/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/t65rdov26nf6k4j6v9hrgidq3u6s@jpeg): #22 of 69 (Elo 1106)
- [The Reversed Rodeo](https://assets.lumenfall.ai/YYRvCt7P1hmJc13F1tg0vsJi42C0TlOnsMTLwOUq6AA/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/iqhq0aqi7hxeo54gdocb5zw0indt@jpeg): #25 of 68 (Elo 1082)
- [Outfit Transfer Challenge](https://assets.lumenfall.ai/AGk9QbM6z_XuW6f_PQJmUi5JyKHfRPj1pzteqa-0xok/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/5cmfbci8wcloylm3qtsdy1q5p12y@jpeg): #18 of 33 (Elo 1066)

## Example Prompt

The following prompt was used to generate an example image in our playground:

A sun-drenched artisan bakery storefront with an elegant gold-leaf sign on the window that reads "FLOUR & BLOOM" in flowing luxury calligraphy. A small, calm capybara sits quietly on the sidewalk next to a basket of baguettes. 1:1, cinematic.

## Code Examples

### Text to Image (/v1/images/generations)

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/generations \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan-2.7",
    "prompt": "",
    "size": "1024x1024"
  }'

# Response:
# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

#### JavaScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.lumenfall.ai/openai/v1'
});

const response = await client.images.generate({
  model: 'wan-2.7',
  prompt: '',
  size: '1024x1024'
});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
console.log(response.data[0].url);

#### Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.lumenfall.ai/openai/v1"
)

response = client.images.generate(
    model="wan-2.7",
    prompt="",
    size="1024x1024"
)

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
print(response.data[0].url)

### Image Edit (/v1/images/edits)

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/edits \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -F "model=wan-2.7" \
  -F "image=@source.png" \
  -F "prompt=Add a starry night sky to this image" \
  -F "size=1024x1024"

# Response:
# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

#### JavaScript

import OpenAI from 'openai';
import fs from 'fs';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.lumenfall.ai/openai/v1'
});

const response = await client.images.edit({
  model: 'wan-2.7',
  image: fs.createReadStream('source.png'),
  prompt: 'Add a starry night sky to this image',
  size: '1024x1024'
});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
console.log(response.data[0].url);

#### Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.lumenfall.ai/openai/v1"
)

response = client.images.edit(
    model="wan-2.7",
    image=open("source.png", "rb"),
    prompt="Add a starry night sky to this image",
    size="1024x1024"
)

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
print(response.data[0].url)


## About

## Overview
Wan 2.4 is an image generation and editing model developed by Alibaba. It is designed to bridge the gap between pure text-to-image synthesis and precise, instruction-based image manipulation. The model is distinctive for its natively integrated support for multiple input modalities, allowing users to generate high-fidelity visuals from text prompts, use reference images to guide the aesthetic, or perform complex edits on existing images using natural language instructions.

## Strengths
*   **Instruction-Based Editing:** The model excels at following precise linguistic instructions to modify existing images, such as adding objects, changing backgrounds, or altering specific attributes while maintaining the integrity of the original composition.
*   **Reference-Guided Synthesis:** Wan 2.4 demonstrates high fidelity when using external images as visual anchors, ensuring that the generated output retains stylistic or structural consistency with the provided reference material.
*   **Semantic Alignment:** It exhibits strong prompt adherence, accurately translating complex or multi-part text descriptions into coherent visual scenes with minimal artifacting in the primary subjects.
*   **Multi-Modal Versatility:** Unlike models restricted to a single input type, Wan 2.4 handles text-to-image, image-to-image, and reference-guided generation within a single framework, streamlining workflows that require iterative refinement.

## Limitations
*   **Sequential Editing Sensitivity:** When performing multiple rounds of instruction-based edits, the model may occasionally introduce "drift," where the original image's fine details gradually lose consistency over repeated transformations.
*   **Contextual Complexity:** While strong at following instructions, the model can struggle with highly technical or spatial layouts that involve more than four or five distinct interacting objects in a single frame.

## Technical Background
Wan 2.4 belongs to the Wan family of generative models, utilizing a diffusion-based architecture optimized for multi-modal inputs. Alibaba implemented a unified latent space approach that treats text prompts and reference images as collaborative tokens, allowing the model to weight visual cues and linguistic instructions simultaneously. The training methodology focused on high-density datasets involving paired image-instruction sets to improve the model's "intent recognition" during the editing process.

## Best For
This model is ideal for creative professionals requiring iterative design workflows, such as rapid prototyping of marketing assets where a base image must be tweaked for different campaigns. It is also well-suited for developers building applications that require dynamic user-driven image modifications or style transfers. 

Wan 2.4 is available through Lumenfall’s unified API and playground, providing a streamlined environment for testing text-to-image prompts and complex image-edit instructions in a single interface.

## Frequently Asked Questions

### How much does Wan 2.7 cost?

Wan 2.7 starts at $0.03 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

### How do I use Wan 2.7 via API?

You can use Wan 2.7 through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "wan-2.7". Code examples are available in Python, JavaScript, and cURL.

### Which providers offer Wan 2.7?

Wan 2.7 is available through Alibaba Cloud on Lumenfall. Lumenfall automatically routes requests to the best available provider.

### What is the maximum resolution for Wan 2.7?

Wan 2.7 supports images up to 2048x2048 resolution.

## Links

- Model Page: https://lumenfall.ai/models/alibaba/wan-2.7
- About: https://lumenfall.ai/models/alibaba/wan-2.7/about
- Providers, Pricing & Performance: https://lumenfall.ai/models/alibaba/wan-2.7/providers
- API Reference: https://lumenfall.ai/models/alibaba/wan-2.7/api
- Benchmarks: https://lumenfall.ai/models/alibaba/wan-2.7/benchmarks
- Use Cases: https://lumenfall.ai/models/alibaba/wan-2.7/use-cases
- Gallery: https://lumenfall.ai/models/alibaba/wan-2.7/gallery
- Playground: https://lumenfall.ai/models/alibaba/wan-2.7/playground
- API Documentation: https://docs.lumenfall.ai