Skip to main content
Image editing

Image editing - Wan2.7/2.6/2.5

Edit images using text instructions with Wan2.7, 2.6, and 2.5 models.

The Wan image editing model series supports multi-image input and output. You can use text instructions to perform tasks such as image editing, multi-image fusion, subject feature preservation, and object detection and segmentation.

Getting started

This example shows how to use the wan2.7-image-pro model to generate an edited image based on two input images and a prompt. Prompt: Spray the graffiti from image 2 onto the car in image 1
Input image 1Input image 2Output image (wan2.7-image-pro)
car
paint
output
  • Synchronous call
  • Asynchronous call
Important Ensure that your DashScope Python SDK is version 1.25.15 or later, and your DashScope Java SDK is version 2.22.13 or later.
import os
import base64
import mimetypes
import urllib.request
import dashscope
from dashscope.aigc.image_generation import ImageGeneration
from dashscope.api_entities.dashscope_response import Message

dashscope.base_http_api_url = "https://dashscope-intl.aliyuncs.com/api/v1"

# If you have not set an environment variable, replace the next line with: api_key="sk-xxx"
api_key = os.getenv("DASHSCOPE_API_KEY")


def encode_file(file_path):
  mime_type, _ = mimetypes.guess_type(file_path)
  if not mime_type or not mime_type.startswith("image/"):
    raise ValueError("Unsupported or unrecognized image format")
  with open(file_path, "rb") as image_file:
    encoded_string = base64.b64encode(image_file.read()).decode("utf-8")
  return f"data:{mime_type};base64,{encoded_string}"


# [Method 1] Use a public image URL
image_1 = "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20251229/pjeqdf/car.webp"
image_2 = "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20251229/xsunlm/paint.webp"

# [Method 2] Use a local file (supports absolute and relative paths)
# image_1 = "file:///path/to/your/car.png"
# image_2 = "file:///path/to/your/paint.png"

# [Method 3] Use a Base64-encoded image
# image_1 = encode_file("/path/to/your/car.png")
# image_2 = encode_file("/path/to/your/paint.png")

message = Message(
  role="user",
  content=[
    {"text": "Spray the graffiti from image 2 onto the car in image 1"},
    {"image": image_1},
    {"image": image_2},
  ],
)
print("----sync call, please wait a moment----")
rsp = ImageGeneration.call(
  model="wan2.7-image-pro",
  api_key=api_key,
  messages=[message],
  watermark=False,
  n=1,
  # wan2.7-image-pro supports 4K only for text-to-image. Image editing supports up to 2K.
  size="2K",
)

if rsp.status_code == 200:
  for i, choice in enumerate(rsp.output.choices):
    for j, content in enumerate(choice["message"]["content"]):
      if content.get("type") == "image":
        image_url = content["image"]
        file_name = f"output_{i}_{j}.png"
        # The result URL is valid for 24 hours. Download it promptly.
        urllib.request.urlretrieve(image_url, file_name)
        print(f"Image saved to {file_name}")
else:
  print(f"Failed: status_code={rsp.status_code}, message={rsp.message}")
Response example
{
    "output": {
        "choices": [
            {
                "finish_reason": "stop",
                "message": {
                    "content": [
                        {
                            "image": "https://dashscope-xxx.oss-xxx.aliyuncs.com/xxx.png?Expires=xxx",
                            "type": "image"
                        }
                    ],
                    "role": "assistant"
                }
            }
        ],
        "finished": true
    },
    "usage": {
        "image_count": 1,
        "input_tokens": 10867,
        "output_tokens": 2,
        "size": "1488*704",
        "total_tokens": 10869
    },
    "request_id": "71dfc3c6-f796-9972-97e4-bc4efc4faxxx"
}
The wan2.5-i2i-preview model uses different API endpoints and parameter formats.

Synchronous call (wan2.5)

Important Make sure your DashScope Python SDK version is at least 1.25.2 and your DashScope Java SDK version is at least 2.22.2.
import base64
import mimetypes
from http import HTTPStatus
from urllib.parse import urlparse, unquote
from pathlib import PurePosixPath

import dashscope
import requests
from dashscope import ImageSynthesis
import os

dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

# If you have not configured an environment variable, replace the next line with: api_key="sk-xxx"
api_key = os.getenv("DASHSCOPE_API_KEY")

# --- Input image: Base64 encoding ---
# Base64 format: data:{MIME_type};base64,{base64_data}
def encode_file(file_path):
    mime_type, _ = mimetypes.guess_type(file_path)
    if not mime_type or not mime_type.startswith("image/"):
        raise ValueError("Unsupported or unrecognized image format")
    with open(file_path, "rb") as image_file:
        encoded_string = base64.b64encode(image_file.read()).decode('utf-8')
    return f"data:{mime_type};base64,{encoded_string}"

"""
Image input methods:
Choose one of the following:

1. Public URL — best for publicly accessible images
2. Local file — best for local development and testing
3. Base64 encoding — best for private images or secure transmission
"""

# [Method 1] Public image URL
image_url_1 = "https://img.alicdn.com/imgextra/i3/O1CN0157XGE51l6iL9441yX_!!6000000004770-49-tps-1104-1472.webp"
image_url_2 = "https://img.alicdn.com/imgextra/i3/O1CN01SfG4J41UYn9WNt4X1_!!6000000002530-49-tps-1696-960.webp"

# [Method 2] Local file (supports absolute and relative paths)
# Format: file:// + file path
# Example (absolute path):
# image_url_1 = "file://" + "/path/to/your/image_1.png"     # Linux/macOS
# image_url_2 = "file://" + "C:/path/to/your/image_2.png"  # Windows
# Example (relative path):
# image_url_1 = "file://" + "./image_1.png"                 # Adjust to your path
# image_url_2 = "file://" + "./image_2.png"                # Adjust to your path

# [Method 3] Base64-encoded image
# image_url_1 = encode_file("./image_1.png")               # Adjust to your path
# image_url_2 = encode_file("./image_2.png")              # Adjust to your path

print('----sync call, please wait a moment----')
rsp = ImageSynthesis.call(api_key=api_key,
                          model="wan2.5-i2i-preview",
                          prompt="Place the alarm clock from image 1 beside the vase on the dining table in image 2.",
                          images=[image_url_1, image_url_2],
                          negative_prompt="",
                          n=1,
                          # size="1280*1280",
                          prompt_extend=True,
                          watermark=False,
                          seed=12345)
print('response: %s' % rsp)
if rsp.status_code == HTTPStatus.OK:
    # Save images to current directory
    for result in rsp.output.results:
        file_name = PurePosixPath(unquote(urlparse(result.url).path)).parts[-1]
        with open('./%s' % file_name, 'wb+') as f:
            f.write(requests.get(result.url).content)
else:
    print('sync_call Failed, status_code: %s, code: %s, message: %s' %
          (rsp.status_code, rsp.code, rsp.message))

Asynchronous call (wan2.5)

Important Make sure your DashScope Python SDK version is at least 1.25.2 and your DashScope Java SDK version is at least 2.22.2.
import os
from http import HTTPStatus
from urllib.parse import urlparse, unquote
from pathlib import PurePosixPath
import dashscope
import requests
from dashscope import ImageSynthesis

dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

# If you have not configured an environment variable, replace the next line with: api_key="sk-xxx"
api_key = os.getenv("DASHSCOPE_API_KEY")

# Public image URLs
image_url_1 = "https://img.alicdn.com/imgextra/i3/O1CN0157XGE51l6iL9441yX_!!6000000004770-49-tps-1104-1472.webp"
image_url_2 = "https://img.alicdn.com/imgextra/i3/O1CN01SfG4J41UYn9WNt4X1_!!6000000002530-49-tps-1696-960.webp"

def async_call():
    print('----create task----')
    task_info = create_async_task()
    print('----wait task----')
    wait_async_task(task_info)

# Create an asynchronous task
def create_async_task():
    rsp = ImageSynthesis.async_call(api_key=api_key,
                                    model="wan2.5-i2i-preview",
                                    prompt="Place the alarm clock from image 1 beside the vase on the dining table in image 2.",
                                    images=[image_url_1, image_url_2],
                                    negative_prompt="",
                                    n=1,
                                    # size="1280*1280",
                                    prompt_extend=True,
                                    watermark=False,
                                    seed=12345)
    print(rsp)
    if rsp.status_code == HTTPStatus.OK:
        print(rsp.output)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' %
              (rsp.status_code, rsp.code, rsp.message))
    return rsp

# Wait for the asynchronous task to finish
def wait_async_task(task):
    rsp = ImageSynthesis.wait(task=task, api_key=api_key)
    print(rsp)
    if rsp.status_code == HTTPStatus.OK:
        print(rsp.output)
        # Save file to current directory
        for result in rsp.output.results:
            file_name = PurePosixPath(unquote(urlparse(result.url).path)).parts[-1]
            with open('./%s' % file_name, 'wb+') as f:
                f.write(requests.get(result.url).content)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' %
              (rsp.status_code, rsp.code, rsp.message))

# Fetch asynchronous task status
def fetch_task_status(task):
    status = ImageSynthesis.fetch(task=task, api_key=api_key)
    print(status)
    if status.status_code == HTTPStatus.OK:
        print(status.output.task_status)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' %
              (status.status_code, status.code, status.message))

# Cancel an asynchronous task. Only PENDING tasks can be canceled.
def cancel_task(task):
    rsp = ImageSynthesis.cancel(task=task, api_key=api_key)
    print(rsp)
    if rsp.status_code == HTTPStatus.OK:
        print(rsp.output.task_status)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' %
              (rsp.status_code, rsp.code, rsp.message))

if __name__ == '__main__':
    async_call()

Demonstration

Generate Image Groups

Input ImageOutput Image
Wan_图片生成_一位 20 岁的东亚男性,头发是卷卷的半长发,文艺气质,五官立体,眉眼清秀,穿着简约白色 T 恤或浅蓝色衬衫,少年感,自然气质。-2026-03-31-19-26-24
output
wan_image_reqid_57d7a71c-1932-4de8-8c32-be0f3fd5696f_n1-2026-03-31-19-32-44
output
Case 1: Photoshoot
Base character setting: A 20-year-old East Asian male with curly, medium-length hair, an artistic temperament, defined features, and delicate eyes. He is wearing a simple white T-shirt or a light blue shirt, exuding a youthful and natural vibe.
1. Republic Era Scholar Style
Prompt:
[Base facial description] The character's appearance is based on reference image 1, wearing a dark cyan long gown and round, gold-rimmed glasses, holding a folding fan. The background is an old Shanghai study with wooden bookshelves, a warm yellow tone, a retro film texture, soft side lighting, and dust dancing in the light beams, creating a cultural and serene atmosphere. Hasselblad medium format, 85mm lens, high resolution, cinematic color grading, Wong Kar-wai style.
Props: Folding fan / Thread-bound book / Round-frame glasses
Color tone: Warm yellow / Dark cyan / Sepia
2. British Gentleman Style
Prompt:
[Base facial description] The character's appearance is based on reference image 1, wearing a dark gray tweed three-piece suit and a vintage mechanical watch, holding a glass of red wine and looking at it. The background is a classic library or private club with dark leather sofas, Rembrandt lighting, and a dark, elegant, and noble atmosphere. He has a cool gaze, with rich details and clear textures, exuding a British aristocratic temperament. 8k resolution, fashion magazine-style shot.
Props: Wine glass / Pipe / Mechanical watch
Color tone: Dark gray / Burgundy / Dark gold
3. 90s HK Retro Style
Prompt:
[Base facial description] The character's appearance is based on reference image 1, wearing a washed denim jacket or a floral shirt, with slightly messy hair and arms crossed. The background is a street with neon signs at night, with blurry light spots, high grain, and rich colors, featuring a red and blue color clash. Wong Kar-wai style, emotional, with a dreamy gaze, direct flash effect, and a nostalgic atmosphere. [Full-body shot].
Color tone: Neon red / Dark blue / Film green
4. New Chinese Zen Style
Prompt:
[Base facial description] The character's appearance is based on reference image 1, with a slight smile showing teeth, wearing a modified white Chinese stand-up collar shirt, holding a branch of plum blossoms. The background is a minimalist blank wall or a bamboo forest, with sunlight casting mottled shadows on the wall. The color tone is cool and serene, embodying Eastern aesthetics. The skin is translucent, with high grain and a matte finish. The composition is simple, with rich layers of light and shadow. High-end photography, Zen atmosphere.
Props: Plum blossom branch
Color tone: White / Dark green / Light gray
5. Vintage Artist Style
Prompt:
[Base facial description] The character's appearance is based on reference image 1, wearing a white shirt stained with paint and a brown leather apron, holding a paintbrush or a palette. The background is a clean studio with bright light and colorful light and shadow. He has a focused expression, looking at the paint in his hand, not at the camera. His hair is slightly messy, with an artistic flair, an impressionist color tone, and a strong texture.
Props: Paintbrush / Palette / Sketchbook
Color tone: Warm light / Colorful paint / Brown
6. Classic Noir B&W Style
Prompt:
[Base facial description] The character's appearance is based on reference image 1, wearing a black turtleneck sweater, holding a cigarette, and wearing a black fedora. The background is a staircase or hallway with intersecting shadows. High-contrast black and white photography, hard lighting, strong shadows, a sense of mystery, and a hard-boiled detective style. The facial contours are sharp, with extremely clear skin texture. A classic movie still, timeless feel, side-profile close-up, artistic photography.
Props: Cane / Fedora / Sunglasses
Color tone: Black and white / High contrast
Case 2: Visual design
Image 1: A commercial-grade product photography main visual cover image, front-view panoramic composition. A pair of retro-futuristic wireless over-ear headphones floats above a geometric plaster form, showcasing perfect symmetrical aesthetics. The materials are champagne gold metal and a cream-white shell. The background is a deeply blurred warm indoor light and shadow, with soft light outlining the product's silhouette. The white space in the image creates a strong sense of breathability, suggesting a quiet auditory experience. 8k ultra-high resolution, minimalist and premium feel.
Image 2: A 100mm macro shot of the product's material details, focusing closely on the connection of the headphone's telescopic arm. It clearly shows the texture of the champagne gold brushed aluminum alloy and the CNC precision-cut chamfers. A sharp backlight creates a starburst highlight on the metal edge. The background is dark to emphasize the industrial precision of the metal. The image quality is extremely sharp with no noise.
Image 3: An extreme close-up macro shot of the material, focusing on the surface of the mocha-colored protein leather earcups. Side lighting reveals the fine pore texture of the leather, the soft wrinkles from pressing, and the ventilation hole details, conveying ultimate skin-friendly comfort and resilience. The light and shadow are rich in layers, and the color tone is warm and moist. Ultra-high-definition macro photography.
Image 4: An artistic exploded view of the product, showing the internal sound units, noise-canceling chips, battery modules, and external walnut wood decorative panels and metal frame of the retro-futuristic headphones in a suspended, disassembled state. The background is a deep tech blue, and the internal components have a semi-transparent holographic technological texture, emphasizing the combination of internal precision craftsmanship and modern technology. High-tech commercial poster style.
Image 5: A 35mm humanistic shot of the wearing scenario, with a close-up on the model's jawline and neck, showing the perfect fit of the champagne gold headphones. Natural warm sunset light from the side-rear creates a rim light, with the edges of the hair glowing gold. The model's skin tone has a healthy and natural texture, creating a relaxed, immersive music-listening lifestyle feel. The background is a blurry home environment.
Image 6: A still life photograph paying homage to architectural light and shadow. The headphones are placed on a minimalist gray concrete table. Afternoon sunlight streams through blinds, casting striped hard shadows that cut across the matte cream-white body and champagne gold frame, creating a strong geometric composition of light and dark. This highlights the three-dimensional shape of the body and the contrast of materials. A clash of cool and warm color tones, minimalist composition.
Image 7: A top-down flat-lay composition showing the color options. Three headphones from the series in different color schemes—silver-white, black-gold, and blue-copper—are arranged side by side. The background is a highly textured gray wool felt cloth. Soft top lighting emphasizes the diversity of the CMF design and the delicate touch of the materials. The image is clean and orderly, in a design magazine style.
Image 8: A brand lifestyle family portrait still life photograph. The retro-futuristic headphones are placed next to their matching exquisite leather case. On the table are a vinyl record player, a spinning vinyl record, and a cup of steaming coffee. The background is rendered with warm ambient lighting, dominated by a deep walnut wood tone, conveying a brand philosophy that combines a slow-paced lifestyle with high-fidelity sound quality. Cinematic narrative lighting.

Multi-Image Fusion

Input ImageOutput Image
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd5304e9d05d028a65a9ac270ee730e44b8c75c6634a9b9a7a70240d438b02b2f2153dc68966b442378d1d4fb4c8ed7016461c-combine
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd53044b9a1d72dee2f8507ee704b9cef3832907ff1182f52507c9bc4737520762d46a722e658f57cda6524fb4c8ed7016461c-2025-12-29-19-11-31
Take a portrait of the boy from image 1 and the dog from image 2. The boy is hugging the dog, and both are very happy. Studio soft lighting, blue textured background.
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd5304f060ec7a363e318af9bfaaa5e07be972cfc1ea4e21b47637fcdb2dfc53130c40a8efed5defc408a04fb4c8ed7016461c-combine
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd5304922cbdef3e3c42f83239de6d0f35a8b76f0e38934cc5170f7a908ec12140fb0af6590c72bcf1ba6f4fb4c8ed7016461c-2025-12-29-19-15-53
Recolor the dress from image 1 using the colors of the bird in image 2. Make it artistic, but keep the style of the dress and the model unchanged.

Subject Feature Preservation

Input ImageOutput Image
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd5304448a972b9f2ee7a7aadcc61495f4975a049f009e7721cbc833dc3a8005b1b026a54eaaec109d73484fb4c8ed7016461c-2025-12-29-20-00-21
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd5304cc1b4a509823c5fb5e60999898811f8b51d7419220a118c9ff82110bc9525725a9ad7338f75985794fb4c8ed7016461c-2025-12-29-20-00-21
Please generate a set of four Polaroid photos with the theme "Seasonal Changes". Each photo is taken at the same location, under a tree in a park, but shows the scenes of spring, summer, autumn, and winter respectively. The person's attire should also match the season: a light jacket in spring, a short-sleeved shirt in summer, a trench coat in autumn, and a scarf and thick coat in winter. Place this set of photos on a dining table.

Detection and Segmentation

Input ImageOutput Image
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd5304b025e74206dc2cec5c2e587c3fe6fb135293836c9479220355470da15476dc934b26018061e9db0b4fb4c8ed7016461c-2025-12-29-19-54-33
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd530451385eb561b49b0fe1f2169526b6a7e15bd78940def3c640c801511c349f6df35dceb72f4d3755f94fb4c8ed7016461c-2025-12-29-19-54-33
Detect the laptop and alarm clock in the image, draw bounding boxes, and label them "laptop" and "clock".
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd530440256f9add4113787af5d4f3a55469b38ef2422f018076640eb7cb552584c02ee729fcb23fec3bca4fb4c8ed7016461c-2025-12-29-19-54-33
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd5304f0612d67f5c810ebef958385624ebd17323047aa5d00465d0e35257de5a2ea49d4b375d2e57693fa4fb4c8ed7016461c-2025-12-29-19-54-32
Segment the glass cup in the image.

Extract Elements

Input ImageOutput Image
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd53046b83761f1ab18c40e144f5db2b388e5f865ba9a5961d98b2710ce177c6a0f4baff63fe52259c44364fb4c8ed7016461c-2025-12-29-19-48-27
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd53048e2a0d1d2805d92ba8d45a3bd1368528dd76f517b21ad1f545eb4097610838497cbdb5196da94ff54fb4c8ed7016461c-2025-12-29-19-48-27
Extract the clothing items from the uploaded photo and arrange them in a flat-lay display on a pure white background. Maintain realistic details and material textures. Fashion e-commerce style, suitable for clothing display.

Text Editing

Input ImageOutput Image
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd530490f493eca22f34f0197173ddfdef17a04b34cb94813178b9d4eee36d246d3530a3e2fc6258cca0694fb4c8ed7016461c-2025-12-29-19-28-35
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd5304fe77776567f4ef79cb621289a6fdaa981f3364fe4c7c56265403b5d9d5ac43eaf5931f62db14952f4fb4c8ed7016461c-2025-12-29-19-28-35
Remove all watermarks from the image.
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd530476e971380812b1b9dbeac68272a27057175499fe84f0781c7b6fa6535f438c67f3556acc8c7324394fb4c8ed7016461c-2025-12-29-19-28-35
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd53047be52c6f41edecdefa77f0d93335d1492f1821b47dff7a1b08f60e99bdafcc84c31e3658fc593c904fb4c8ed7016461c-2025-12-29-19-28-35
Casually write "Time for Holiday?" on the sand with a hand.
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd5304fdb284f8d5c8ead814d11890da1a49411a6d9d41ad1bb2a4bf0b93d0bee5d792e8f5b419a3da9d534fb4c8ed7016461c-2025-12-29-19-28-34
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd5304df1c8787530497f4cc3bee0b84d3ba51d0353fceb8d0518ded6a25e8c0ddfec714f719154ac1c9354fb4c8ed7016461c-2025-12-29-19-28-34
Change 18 to 29 and JUNE to SEPTEMBER.

Lens and Viewpoint Editing

Input ImageOutput Image
image (2)-2025-12-29-19-42-44
image (3)-2025-12-29-19-42-44
Keep the person's features unchanged and generate front, side, and back views.
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd5304a53988b2efdd2fb6b95cb3b1b02701e6ff2c4902170b1ee230a9b4e3726a891c93646d68b821de294fb4c8ed7016461c-2025-12-29-19-42-43
5eecdaf48460cde5544f9fac410016bc2fe4c1b4d23666c075b8339e1c4c24831b75b38faadcd24bec177c308ebd530428783dee341e41eb06234dfb75bd149d774f4850000123559a98bcd7ece97dc4a6c3cefa983ae8ac4fb4c8ed7016461c-2025-12-29-19-42-43
Reshoot this photo with a fisheye lens.

Input instructions

Input image specifications

Specificationwan2.7-image-pro, wan2.7-imagewan2.6-imagewan2.5-i2i-preview
Number of input images0 to 9 (0 for text-to-image mode)Image editing: 1 to 4 / Mixed media: 0 to 11 to 3
Image formatJPEG, JPG, PNG (alpha channel not supported), BMP, WEBPJPEG, JPG, PNG (alpha channel not supported), BMP, WEBPJPEG, JPG, PNG (alpha channel not supported), BMP, WEBP
Image dimensions[240, 8000] pixels[240, 8000] pixels[384, 5000] pixels
File size≤ 20 MB≤ 10 MB≤ 10 MB
Aspect ratio[1:8, 8:1]No limit[1:4, 4:1]

Image input order

Input image 1Input image 2Output image
image (19)-转换自-png
Image 1
image (20)-转换自-png
Image 2
04e0fc39-7ad6-41e0-9df9-1f69ac3ce825-转换自-png
Prompt: Move Image 1 onto Image 2
36ed450d-bd54-4169-b13f-3d0f26d9d360-转换自-png
Prompt: Move Image 2 onto Image 1

Methods for providing images

Provide images in the following ways:
# Use a publicly accessible image URL
image_url = "https://example.com/your-image.png"
# In curl, pass the URL directly in the JSON body
"image": "https://example.com/your-image.png"
import os
import base64
import mimetypes

# The format is data:{mime_type};base64,{base64_data}
def encode_file(file_path):
    mime_type, _ = mimetypes.guess_type(file_path)
    with open(file_path, "rb") as image_file:
        encoded_string = base64.b64encode(image_file.read()).decode('utf-8')
    return f"data:{mime_type};base64,{encoded_string}"
        
        
# Call the encoding function. Replace "/path/to/your/image.png" with the path to your local image file. Otherwise, the code will not run.
image = encode_file("/path/to/your/image.png")
# Local file path format: file:// + absolute path
# Linux/macOS example:
image_url = "file://" + "/path/to/your/image.png"
# Windows example:
image_url = "file:///" + "C:/path/to/your/image.png"

# Relative path example:
image_url = "file://" + "./your-image.png"
This method is only supported by the SDK. Curl requests require a public URL or Base64 encoding.

Key capabilities

1. Instruction following (prompts)

The parameters are messages.content.text or input.prompt (required), and negative_prompt (optional).
Parameterwan2.7-image-pro, wan2.7-imagewan2.6-imagewan2.5-i2i-preview
textRequired, up to 5000 charactersRequired, up to 2000 charactersNot supported
promptNot supportedNot supportedRequired, up to 2000 characters
negative_promptNot supportedSupported, up to 500 charactersSupported, up to 500 characters

2. Enable prompt rewriting

The parameter is parameters.prompt_extend (bool, default true ). This feature automatically expands and optimizes short prompts to improve output image quality. However, enabling it adds extra processing time.
Parameterwan2.7-image-pro, wan2.7-imagewan2.6-imagewan2.5-i2i-preview
prompt_extendNot supportedSupported (edit mode only)Supported

3. Set output image resolution

The parameter is parameters.size (string), formatted as "width*height" .
Parameterwan2.7-image-pro, wan2.7-imagewan2.6-imagewan2.5-i2i-preview
sizeOption 1: Specify output resolution (recommended) In edit mode (at least one input image provided), choose from these resolution presets: 1K , 2K (default). 1K : Output has approximately 1024×1024 total pixels, preserving the aspect ratio of the last input image. 2K : Output has approximately 2048×2048 total pixels, preserving the aspect ratio of the last input image. Option 2: Specify exact width and height in pixels Total pixels must be between 768×768 and 2048×2048, with an aspect ratio between 1:8 and 8:1. Only wan2.7-image-pro in text-to-image scenarios supports 4K resolution.Option 1: Match input image aspect ratio (recommended) In edit mode ( enable_interleave=false ), choose from these resolution presets: 1K (default), 2K . 1K : Output has approximately 1280×1280 total pixels, preserving the aspect ratio of the last input image. 2K : Output has approximately 2048×2048 total pixels, preserving the aspect ratio of the last input image. Option 2: Specify exact width and height in pixels Total pixels must be between 768×768 and 2048×2048, with an aspect ratio between 1:4 and 4:1. The pixel value of the actual output image is a multiple of 16 that is closest to the specified value.Only exact width and height in pixels are supported Total pixels must be between 768×768 and 1280×1280, with an aspect ratio between 1:4 and 4:1. If you do not specify size , the system generates an image with a total of 1280*1280 pixels by default, with the same aspect ratio as the last input image.

4. Interactive precise editing

You can use the parameters.bbox_list parameter to define interactive editing regions. The format is List[List[List[int]]] . This lets you select specific objects or areas in the image for more accurate edits. Only wan2.7-image-pro and wan2.7-image support this feature. For example, if the input includes 3 images, and Image 2 has no selections while Image 1 has two selections, you would use the following:
[
  [[0, 0, 12, 12], [25, 25, 100, 100]],  # Image 1 (2 boxes)
  [],                                    # Image 2 (no boxes)
  [[10, 10, 50, 50]]                    # Image 3 (1 box)
]

Billing and Rate Limits

  • For free quota and pricing details, see Pricing.
  • For rate limit details, see Rate Limits.
  • Billing details: You are billed for each successfully generated image. Charges are incurred only when the API returns a task_status of SUCCEEDED and an image is generated. You are not charged for failed calls or processing errors, and they do not consume your free quota.

API Reference

For information about input and output parameters, see Wan - Image Generation and Editing (for wan2.7-image and wan2.6-image) and Wan - General Image Editing 2.5 API Reference.