Image models › Qwen

Qwen3 Pro Image to Image

Qwen3 Pro Image to Image

image Qwen 9 tokens per image $0.005 per token

Pricing

OptionTokensUnit≈ USD
input, 2K1per image$0.0050
input, 1K1per image$0.0050
output, 1K9per image$0.0450
output, 2K16per image$0.0800

The price is held when the task is created and settled to actual consumption when it completes; a failed task releases the hold.

How to order

This is the image-to-image twin of qwen3-pro-text-to-image: create the series with that id in model and attach reference images — the service switches to this model by itself. Its own id is not accepted in a series.

POST https://app.video-blade.com/api/v1/projects/{id}/image-series
X-API-Key: vb_…
Content-Type: application/json

{"title": "…", "prompt": "…", "model": "qwen3-pro-text-to-image", "aspect_ratio": "9:16", "count": 2, "references": [{"url": "https://…"}]}

POST https://app.video-blade.com/api/v1/projects/{id}/image-series/{item_id}/generate
→ 202 {"generation_ids": ["…"], "status": "running", "tokens_held": …}

Field lists and refusal codes — API reference.

Model parameters

What the model itself understands; the ordering calls above take their own fields and pass these on.

NameTypeRequiredDescription
image_urls array required Input image URL array. Upload images and provide their URLs rather than the file content. Supports up to 3 images. Supported file types: `image/jpeg`, `image/png`, `image/webp`, `image/bmp`, and `image/gif`,`image/tiff`. Maximum file size: 10 MB per image.
prompt string required The positive prompt that describes the image content, style, and composition you want to generate or edit. Both Chinese and English are supported.
resolution string optional The output image resolution.
Values: 1K, 2K
Default: 1K
image_size string optional The output image size.
Values: 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9
Default: 16:9
output_format string optional The generated image format.
Values: png, jpeg
Default: png
prompt_extend boolean optional Whether to enable intelligent prompt rewriting. Default: true (recommended). When enabled, the model optimizes the positive prompt, which significantly improves results for simple descriptions.
Default: True
nsfw_checker boolean optional Whether to enable content filtering. Optional. Defaults to false. When set to false, content filtering is disabled and all results are returned directly by the model. Note: Content filtering cannot guarantee that all inappropriate content will be detected. If the filtering results do not meet your requirements, you must implement additional content moderation measures.
Default: False
negative_prompt string optional The negative prompt that describes content you do not want to appear in the image.
seed integer optional The random seed. Value range: [0, 2147483647]. A fixed seed helps maintain relatively stable results.
Default: 1