Alibaba

Wan 2.7

Name: Wan 2.7
Brand: Alibaba
Price: 0.03 USD
Availability: InStock

AI Image Editing Model

Mode:

Image

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

Wan 2.7 generated image of A meticulously detailed close-up of an elderly artisan's hands carving an int...

Try Model Benchmark examples

2048 x 2048

Max Resolution

Max Images per Request

Supported Modes

Text to Image Image Edit

Active

Details

Model ID

wan-2.7

Also known as: wan2.7-image

Creator

Alibaba

Family

wan

Released

April 2026

Max Input Images

Ready to integrate?

Access wan-2.7 via our unified API.

Create Account

Available at 1 provider

Starting from

$0.030 /image via Alibaba Cloud

Prices shown are in USD

Full pricing details

Provider Performance

Fastest generation through alibaba at 12,086ms median latency with 91.3% success rate.

Aggregated from real API requests over the last 30 days.

Generation Time

alibaba

p95: 27,249ms

Success Rate

alibaba

91.3%

21 / 23 requests

Time to First Byte

alibaba

10,161ms

p95: 24,060ms

Provider Rankings

#	Provider	p50 Gen Time	p95 Gen Time	Success Rate	TTFB (p50)
1	alibaba	12,086ms	27,249ms	91.3%	10,161ms

Data updated every 15 minutes. Based on all API requests through Lumenfall over the last 30 days.

Providers & Pricing (1)

Wan 2.7 is available exclusively through Alibaba Cloud, starting at $0.03/image.

Alibaba Cloud

Text to Image Image Edit

alibaba/wan-2.7-image

Provider Model ID: wan2.7-image

$0.030 /image

wan2.7-image API OpenAI-compatible

Access Wan 2.7 through Lumenfall’s OpenAI-compatible API to programmatically generate high-fidelity images and execute complex reference-guided image edits.

Base URL

https://api.lumenfall.ai/openai/v1

Model

wan-2.7

Code Examples

Text to Image

/v1/images/generations

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": "..." }] }

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);

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 -X POST \

  https://api.lumenfall.ai/openai/v1/images/edits \

  -H "Authorization: Bearer $LUMENFALL_API_KEY" \

  -F "model=wan-2.7" \

  -F "[email protected]" \

  -F "prompt=Add a starry night sky to this image" \

  -F "size=1024x1024"

# Response:

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

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);

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)

Parameter Reference

Required Supported Not available

Core Parameters

Parameter	Type	Description	Modes
`prompt`	string	Required. Text prompt for image generation	T2I Edit
`seed`	integer	Random seed for reproducibility	T2I Edit

Size & Layout

Parameter	Type	Description	Modes
`size`	string	Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9") WxH determines both shape and scale (aspect_ratio and resolution are ignored when size is provided). W:H format is equivalent to aspect_ratio.	T2I Edit
`aspect_ratio`	string	Aspect ratio of the output image (e.g. "16:9", "1:1") Controls shape independently of scale. Use with resolution to control both. If size is also provided, size takes precedence. Any ratio is accepted and mapped to the nearest supported value.	T2I Edit
`resolution`	string	Output resolution tier (e.g. "1K", "4K") Controls scale independently of shape. Higher tiers produce larger images and cost more. If size is also provided, size takes precedence for scale. Any tier is accepted and mapped to the nearest supported value.	T2I Edit

size

Exact pixel dimensions

"1920x1080"

aspect_ratio

Shape only, default scale

"16:9"

resolution

Scale tier, preserves shape

"1K"

Priority when combined

size › aspect_ratio + resolution › aspect_ratio › resolution

size is most specific and always wins. aspect_ratio and resolution control shape and scale independently.

How matching works

Shape matching – we pick the closest supported ratio. Ask for 7:1 on a model with 4:1 and 8:1, you get 8:1.

Scale matching – providers use different tier formats: K tiers (0.5K 1K 2K 4K) or megapixel tiers (0.25 1). If the exact tier isn't available, you get the nearest one.

Dimension clamping – if a model has pixel limits, we clamp dimensions to fit and keep the aspect ratio intact.

Media Inputs

Parameter	Type	Description	Modes
`image`	file	Required. Input image(s) to edit Supports PNG, JPEG, WebP. Up to 9 images per request.	T2I Edit

Output & Format

Parameter	Type	Description	Modes
`response_format`	string	How to return the image `url` `b64_json` Default: `"url"`	T2I Edit
`output_format`	string	Output image format `png` `jpeg` `gif` `webp` `avif` Gateway converts to requested format if provider doesn't support it natively.	T2I Edit
`output_compression`	integer	Compression level for lossy formats (JPEG, WebP, AVIF)	T2I Edit
`n`	integer	Number of images to generate Default: `1` Gateway generates multiple images in parallel even if provider only supports 1.	T2I Edit

Additional Parameters

Provider-specific passthrough fields, available only when the request is routed to the listed provider.

Parameter	Type	Description	Modes
Universal
`thinking`	string	Model's internal reasoning effort (off, on, minimal, high) `off` `on`	T2I Edit
alibaba
`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.	T2I Edit
`color_palette`	array	Optional custom color theme, available only when image-set mode is disabled.	T2I Edit
`enable_sequential`	boolean	Whether to enable image-set output mode.	T2I Edit
`watermark`	boolean	Whether to add the provider watermark to the generated media.	T2I Edit

Parameter Normalization

How we handle parameters across different providers

Not every provider speaks the same language. When you send a parameter, we handle it in one of four ways depending on what the model supports:

Behavior	What happens	Example
`passthrough`	Sent as-is to the provider	style, quality
`renamed`	Same value, mapped to the field name the provider expects	prompt
`converted`	Transformed to the provider's native format	size
`emulated`	Works even if the provider has no concept of it	n, response_format

Parameters we don't recognize pass straight through to the upstream API, so provider-specific options still work.

Full API Reference Authentication, endpoints, and more

Wan 2.7 Benchmarks

Wan 2.7 is ranked #43 in Text-to-Image with an Elo of 1206 and #20 in Image Editing with an Elo of 1168 on the Lumenfall Arena, where real users pick the better image in blind comparisons. These rankings are based on 4 blind-vote competitions.

Lumenfall Arena

#43

Text-to-Image

1206 Elo

Lumenfall Arena

#20

Image Editing

1168 Elo

Text-to-Image Landscape

Elo vs Cost

1 model without pricing omitted.

Image Editing Landscape

Elo vs Cost

1 model without pricing omitted.

Competition Results

Text-to-Image

Prompt Adherence

View leaderboard

#17

The Capybara Taxi Driver

69 models

Text-to-Image

Prompt

“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”

#25

The Reversed Rodeo

68 models

Text-to-Image

Prompt

“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”

#37

Chalkboard Menu

69 models

Text-to-Image

Prompt

“Handwritten-style chalkboard menu in a cozy café, all text rendered in the exact same realistic chalk handwriting style with natural variations in letter size, slight slant, and chalk texture — no printed or digital fonts anywhere on the board. Title at the top in elegant cursive chalk handwriting: ‘TODAY’S SPECIALS – APRIL 30, 2026’. Below it, three menu items also in the same handwritten chalk style: ‘Truffle Mushroom Risotto – $24’, ‘Grilled Octopus with Lemon & Herbs – $28’, ‘Brown Butter Chocolate Chip Cookies – $9’. At the very bottom, smaller text in the identical handwritten chalk style (slightly smaller but still clearly legible with the same handwriting characteristics): ‘All items made fresh daily • Ask about our gluten-free options’. Warm ambient café lighting, visible chalk dust and smudges, realistic handwriting imperfections, no clean printed text anywhere.”

Image Editing

Prompt Adherence

View leaderboard

#18

Outfit Transfer Challenge

33 models

Image Editing

Source

Edit instruction

“Use Image 1 as the base person. Dress them in the exact elaborate outfit from Image 2 (including all layers, accessories, jewelry, and shoes). Carefully adapt the clothing to the body shape and pose in Image 1 while maintaining realistic fabric behavior, correct proportions, and perfect lighting/shadow matching. Keep the person’s exact face, hair, and background completely unchanged.”

Text-to-Image

Aesthetics

View leaderboard

#17

The Capybara Taxi Driver

69 models

Text-to-Image

Prompt

#25

The Reversed Rodeo

68 models

Text-to-Image

Prompt

“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”

Text-to-Image

Creativity

View leaderboard

#25

The Reversed Rodeo

68 models

Text-to-Image

Prompt

“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”

Text-to-Image

Photorealism

View leaderboard

#17

The Capybara Taxi Driver

69 models

Text-to-Image

Prompt

#25

The Reversed Rodeo

68 models

Text-to-Image

Prompt

“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”

#37

Chalkboard Menu

69 models

Text-to-Image

Prompt

Image Editing

Photorealism

View leaderboard

#18

Outfit Transfer Challenge

33 models

Image Editing

Source

Edit instruction

Text-to-Image

Text Rendering

View leaderboard

#37

Chalkboard Menu

69 models

Text-to-Image

Prompt

Image Editing

Preservation

View leaderboard

#18

Outfit Transfer Challenge

33 models

Image Editing

Source

Edit instruction

Text-to-Image

Art

View leaderboard

#25

The Reversed Rodeo

68 models

Text-to-Image

Prompt

“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”

Image Editing

Adding & Editing Objects

View leaderboard

#18

Outfit Transfer Challenge

33 models

Image Editing

Source

Edit instruction

Image Editing

Lighting, Shadows & Materials

View leaderboard

#18

Outfit Transfer Challenge

33 models

Image Editing

Source

Edit instruction

Text-to-Image

Product, Branding & Commercial

View leaderboard

#37

Chalkboard Menu

69 models

Text-to-Image

Prompt

Top Matchups

See how Wan 2.7 performs head-to-head against other AI models, ranked by community votes in blind comparisons.

The Capybara Taxi Driver

Wan 2.7 Z-Image Turbo

0% 100%

Pose & Character Mashup

Wan 2.7 GPT Image 2

0% 100%

Use Cases

See all Use Cases

#20 of 33

Preservation

Edit · 42.9% win rate

#19 of 30

Lighting, Shadows & Materials

Edit · 41.7% win rate

Gallery

View all 8 images

Wan 2.7 FAQ

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.

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.

Try Wan 2.7 in Playground

Generate images with custom prompts — no API key needed.

Open Playground

Details

Ready to integrate?

Generation Time

Success Rate

Time to First Byte

Provider Rankings

Providers & Pricing (1)

Code Examples

Text to Image

Image Edit

Parameter Reference

Core Parameters

Size & Layout

Priority when combined

How matching works

Media Inputs

Output & Format

Additional Parameters

Parameter Normalization

Wan 2.7 Benchmarks

Text-to-Image Landscape

Elo vs Cost

Elo vs Speed

Image Editing Landscape

Elo vs Cost

Elo vs Speed

Competition Results

Prompt Adherence

Prompt Adherence

Aesthetics

Creativity

Photorealism

Photorealism

Text Rendering

Preservation

Art

Adding & Editing Objects

Lighting, Shadows & Materials

Product, Branding & Commercial

Top Matchups

Use Cases

Gallery

Wan 2.7 FAQ

Overview

Strengths

Limitations

Technical Background

Best For

Try Wan 2.7 in Playground