Qwen Image 3.0
Text to image · Image editing
Starting price $0.07 / image
By Alibaba
Alibaba's Wan 2.6 Image creates an image from a prompt in English or Chinese, or edits a photo and combines up to three reference images from a written instruction.
wan/v2.6/image-to-imageThis model has other modes with their own ids: wan/v2.6/text-to-image.
Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.
# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan/v2.6/image-to-image",
"input": {
"prompt": "Put the ceramic vase from the first image on the wooden table in the second image, in the same soft afternoon light, and keep the vase'\''s color and pattern.",
"image_urls": [
"https://example.com/input.png"
]
}
}'
# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{"model": "wan/v2.6/image-to-image", "quote_id": "QUOTE_ID", "input": {"prompt":"Put the ceramic vase from the first image on the wooden table in the second image, in the same soft afternoon light, and keep the vase'\''s color and pattern.","image_urls":["https://example.com/input.png"]}}'
# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
-H "Authorization: Bearer $RAYWAKE_API_KEY"| Name | Type | Description |
|---|---|---|
promptrequired | string | Text prompt describing the desired image. Supports Chinese and English. Max 2000 characters. Example: 'Generate an image using the style of image 1 and background of image 2'. |
image_urlsrequired | array of image URLs | Reference images for editing (1-3 images required). Order matters: reference as 'image 1', 'image 2', 'image 3' in prompt. Resolution: 384-5000px each dimension. Max size: 10MB each. Formats: JPEG, JPG, PNG (no alpha), BMP, WEBP. |
negative_prompt | string | Content to avoid in the generated image. Max 500 characters. |
image_size | string (enum) | Output image size. Total pixels must be between 768×768 and 1280×1280. |
num_images | integer | Number of images to generate (1-4). |
enable_prompt_expansion | boolean | Enable LLM prompt optimization. Significantly improves results for simple prompts but adds 3-4 seconds processing time. |
seed | integer | Random seed for reproducibility (0-2147483647). Same seed produces more consistent results. |
A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.
"outputs": [
{ "type": "image", "url": "https://…", "mime_type": "image/png", "thumbnail_url": "https://…" }
]The exact charge for your input comes from a quote. How charges settle
Fields marked * are required. Review the price before generating.
Wan 2.6 Image takes a prompt of up to 2000 characters and a negative prompt of up to 500. Add one reference image to steer the look; without a size preset, the result follows the reference's size up to 1280 × 1280.
The edit mode takes one to three images, which you refer to by their order in the prompt, and returns one to four images in six preset sizes. Prompt expansion is on by default and rewrites short prompts into fuller ones.
Inspect the full-size output and compare details and subject appearance with your source.