# Wan 2.7 Pro

> Alibaba's Wan 2.7 Pro image generation and editing model with higher-quality outputs and support for 4K image generation

## Quick Reference

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

## Specifications

- Max Resolution: 4096x4096
- 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-pro?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-pro
- Aliases: wan2.7-image-pro

## Dates

- Released: April 2026

## Tags

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

## Available Providers

### Alibaba Cloud

- Config Key: alibaba/wan-2.7-pro-image
- Provider Model ID: wan2.7-image-pro
- Pricing: $0.075/image


## Performance Metrics

Provider performance over the last 30 days.

### alibaba

- Median Generation Time (p50): 15273ms
- 95th Percentile Generation Time (p95): 52604ms
- Average Generation Time: 22725ms
- Success Rate: 100.0%
- Total Requests: 15
- Time to First Byte (p50): 12170ms
- Time to First Byte (p95): 47018ms


## Arena Benchmarks

### Magic Burger Explosion: Fiery Photorealism Challenge

- Elo: 1188
- Record: 7W / 8L / 1T (16 battles)
- Rank: #4 of 69

### The Capybara Taxi Driver

- Elo: 1185
- Record: 7W / 6L / 2T (15 battles)
- Rank: #6 of 69

### Pose & Character Mashup

- Elo: 1066
- Record: 3W / 5L / 4T (12 battles)
- Rank: #14 of 33

### Chalkboard Menu

- Elo: 1054
- Record: 1W / 5L / 0T (6 battles)
- Rank: #44 of 69


## Use Cases & Category Performance

### Aesthetics (Text-to-Image)

- Rank: #25 of 62
- Elo: 1226
- Record: 20W / 16L / 4T (40 battles)
- Win Rate: 50.0%

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

- Rank: #30 of 61
- Elo: 1219
- Record: 18W / 21L / 4T (43 battles)
- Win Rate: 41.9%

### Photorealism (Text-to-Image)

- Rank: #31 of 62
- Elo: 1182
- Record: 17W / 20L / 4T (41 battles)
- Win Rate: 41.5%

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

- Rank: #38 of 61
- Elo: 1184
- Record: 12W / 15L / 1T (28 battles)
- Win Rate: 42.9%

### Preservation (Image Editing)

- Rank: #23 of 33
- Elo: 1149
- Record: 4W / 6L / 5T (15 battles)
- Win Rate: 26.7%

### Prompt Adherence (Image Editing)

- Rank: #17 of 24
- Elo: 1152
- Record: 4W / 6L / 5T (15 battles)
- Win Rate: 26.7%

### Art (Text-to-Image)

- Rank: #22 of 31
- Elo: 1126
- Record: 2W / 1L / 1T (4 battles)
- Win Rate: 50.0%

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

- Rank: #43 of 61
- Elo: 1172
- Record: 10W / 15L / 1T (26 battles)
- Win Rate: 38.5%

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

- Rank: #22 of 30
- Elo: 1167
- Record: 4W / 6L / 5T (15 battles)
- Win Rate: 26.7%

### Creativity (Text-to-Image)

- Rank: #51 of 62
- Elo: 1148
- Record: 4W / 2L / 1T (7 battles)
- Win Rate: 57.1%

### People & Poses (Image Editing)

- Rank: #16 of 18
- Elo: 1154
- Record: 3W / 5L / 4T (12 battles)
- Win Rate: 25.0%


## Image Gallery

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

### Curated Examples

- [A wide-angle cinematic shot of a luxury boutique storefront at dusk, where the name "Wan 2.7 Pro"...](https://assets.lumenfall.ai/CVRXJUYrhmU-KbWWoBhyfJ5bLaZoN_ynUBJGFtXKrBA/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/ta7l5vzai6n4tl3bkl0n2skpu4fm@jpeg)
- [A medium shot of an elderly artisan in a sun-drenched Mediterranean workshop, meticulously carvin...](https://assets.lumenfall.ai/eBvnk-lx2fcKdwIgGu5spqtxBoJQmVME6LNVWvz4HzE/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/44rz35b2api1l1vd9ecy4p3ewo4z@jpeg)
- [A hyper-realistic close-up of a weathered, wooden artisan’s workbench scattered with vintage watc...](https://assets.lumenfall.ai/by-MZ0l6P0TcSZ4IQJiwRLrnB7il0I8oFMGo62EQvmA/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/f488rylcfntapcxesmsko6o8x94c@jpeg)
- [A beautiful hand-painted ceramic bowl sitting on a rustic wooden table, filled with fresh lemons....](https://assets.lumenfall.ai/ZW1kU9rscHXZXlktDysZbi4vSx_JgpU9d49LKmVhccw/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/5wu0rtotalv5t9fug7rmjtrbtscd@jpeg)

### Arena Competition Results

- [Magic Burger Explosion: Fiery Photorealism Challenge](https://assets.lumenfall.ai/ap2-ncbn2MiaFKgmLXpR34N7vwtOAGushs5ieLNmScI/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/sn5h3atcj5yr227jpyvy4xslj6h5@jpeg): #4 of 69 (Elo 1188)
- [The Capybara Taxi Driver](https://assets.lumenfall.ai/dMqtprSbtIo6Ubg0QYs5krosynPbxZZHrr7c3Cay2ag/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/z48umzep799ektkfa445jct7kay1@jpeg): #6 of 69 (Elo 1185)
- [Pose & Character Mashup](https://assets.lumenfall.ai/mRGVS-iV8_AxjxOzKT1rlEhigLE909loY9X7AyFW7UA/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/2r4z93m8pj885x95rx9z0eafeyy2@jpeg): #14 of 33 (Elo 1066)
- [Chalkboard Menu](https://assets.lumenfall.ai/bRC5e682woCj44LfLEiMZ03MTtqf5VQ9nxIv6nRQAJI/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/ma7cztikjt47kvxattr0qtghthex@jpeg): #44 of 69 (Elo 1054)

## Example Prompt

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

A beautiful hand-painted ceramic bowl sitting on a rustic wooden table, filled with fresh lemons. The text "Zesty & Sweet" is elegantly embossed in gold script on the side of the bowl. In the soft-focus garden background, a capybara naps in the sun.

## 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-pro",
    "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-pro',
  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-pro",
    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-pro" \
  -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-pro',
  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-pro",
    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 2.7 Pro is a high-resolution diffusion model developed by Alibaba designed for advanced image synthesis and sophisticated image-to-image editing. It represents a significant iteration in the Wan model family, distinguished by its native support for 4K resolution output and enhanced spatial coherence. The model allows users to generate visual content from natural language descriptions or modify existing images through precise editing workflows.

## Strengths
*   **High-Resolution Fidelity:** Supports native 4K image generation, maintaining sharp textures and fine details that often blur or artifact in lower-resolution models.
*   **Multi-Image Contextual Awareness:** Excels at tasks requiring the synthesis of information across multiple input images, making it effective for consistent character rendering or style transfer.
*   **Precise Image Editing:** The model provides high control during image-to-image tasks, allowing for structural modifications while preserving the overall composition and lighting of the source material.
*   **Complex Prompt Adherence:** Demonstrates improved understanding of lengthy, descriptive prompts, accurately mapping nested attributes and spatial relationships to the final output.

## Limitations
*   **Hardware and Latency Requirements:** Due to the complexity of 4K synthesis and the model's architecture, generation times are typically longer compared to "Turbo" or distilled small-scale models.
*   **Specific Aesthetic Bias:** Like many models in the Wan family, it may lean toward a specific digital art style or photorealistic polish that might require prompt engineering to override for more stylized or abstract requests.

## Technical Background
Wan 2.7 Pro is built on an evolution of the DiT (Diffusion Transformer) architecture, optimized for handling massive spatial dimensions without losing global consistency. The training process involved a multi-stage approach, utilizing a curated dataset of high-resolution imagery and detailed captioning to improve the alignment between text tokens and visual patches. This version introduces refined attention mechanisms to manage the computational overhead of 4K processing while maintaining high signal-to-noise ratios.

## Best For
This model is best suited for professional workflows where output resolution and detail are non-negotiable, such as digital marketing assets, background plates for VFX, and high-end conceptual art. Its image-editing capabilities make it a strong choice for iterative design cycles where an artist needs to transform a sketch or a low-fidelity reference into a production-ready asset. Wan 2.7 Pro is available for testing and integration through Lumenfall’s unified API and interactive playground.

## Frequently Asked Questions

### How much does Wan 2.7 Pro cost?

Wan 2.7 Pro starts at $0.075 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

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

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

### Which providers offer Wan 2.7 Pro?

Wan 2.7 Pro 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 Pro?

Wan 2.7 Pro supports images up to 4096x4096 resolution.

## Links

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