Qwen Image 3.0
Text to image · Image editing
Starting price $0.07 / image
By Alibaba
Wan 2.2 A14B Image creates images from a written prompt and reworks an image you upload, with two guidance stages you can tune.
wan/v2.2-a14b/text-to-imageThis model has other modes with their own ids: wan/v2.2-a14b/image-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/v2.2-a14b/text-to-image",
"input": {
"prompt": "A street food vendor cooking at night under a bare light bulb, steam rising from the wok, blurred city lights behind, candid photo style."
}
}'
# 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/v2.2-a14b/text-to-image", "quote_id": "QUOTE_ID", "input": {"prompt":"A street food vendor cooking at night under a bare light bulb, steam rising from the wok, blurred city lights behind, candid photo style."}}'
# 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 | The text prompt to guide image generation. |
negative_prompt | string | Negative prompt for video generation. |
seed | integer | Random seed for reproducibility. If None, a random seed is chosen. |
num_inference_steps | integer | Number of inference steps for sampling. Higher values give better quality but take longer. |
enable_prompt_expansion | boolean | Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning. |
acceleration | string (enum) | Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'. |
guidance_scale | number | Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality. |
guidance_scale_2 | number | Guidance scale for the second stage of the model. This is used to control the adherence to the prompt in the second stage of the model. |
shift | number | Shift value for the image. Must be between 1.0 and 10.0. |
image_size | string (enum) | The size of the generated image. |
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 2.2 A14B Image makes images in six preset shapes, with an optional negative prompt and prompt expansion. It works in two stages, and each has its own guidance scale; steps and shift are adjustable too.
The image-to-image mode starts from your picture. Strength sets how much changes: 0 keeps the original and 1 remakes it fully. The shape can follow your image or be set to 16:9, 9:16 or 1:1.
Inspect fine textures and geometry; for edits, compare the preserved subject with the source.