> ## Documentation Index > Fetch the complete documentation index at: https://docs.magnific.com/llms.txt > Use this file to discover all available pages before exploring further. # Qwen Image 3.0 API > Generate and edit images with Qwen Image 3.0 from Alibaba. Text-to-image or editing with up to 3 input images, 10 aspect ratios and negative prompts. > [card] Qwen Image 3.0 > > Generate an image from a prompt, or edit and combine up to three images with a text instruction. Qwen Image 3.0 is Alibaba's image generation and editing model. One endpoint covers both: send a `prompt` alone to generate an image, or add up to three `images` to edit or combine them. It renders at about 1 megapixel in 10 aspect ratios. For higher resolution, see [Qwen Image 3.0 Pro](https://docs.magnific.com/api-reference/text-to-image/qwen-image-3-pro/overview.md). ### Key capabilities * **Generation and editing in one endpoint**: Text-to-image, or edit with up to **3** `images` * **Refer to images by position**: `image 1`, `image 2`, `image 3`, in the order you send them * **Aspect ratios**: 10 ratios from `2:1` to `1:2` at about 1 megapixel * **Flat price**: one price per image, whatever the parameters * **Negative prompt** and **seed** control * **Prompt range**: 1 to 10,000 characters * **Async processing**: Webhook notification or polling for task completion ### Use cases * **Product and marketing images**: Generate scenes, posters and social graphics from a description * **Image edits**: Change an element, the background or the style of an image while keeping the rest * **Composition**: Combine up to three images, e.g. *"put the product from image 2 on the table in image 1"* * **Restyling**: Turn a photo into an illustration, watercolor or sketch ### API operations Create an image with the POST endpoint, then track it with the list and status endpoints. Generation returns a task ID for async polling or webhook notification. > [card] [POST /v1/ai/text-to-image/qwen-image-3](https://docs.magnific.com/api-reference/text-to-image/qwen-image-3/generate.md) > > Create a new image generation or editing task > [card] [GET /v1/ai/text-to-image/qwen-image-3](https://docs.magnific.com/api-reference/text-to-image/qwen-image-3/qwen-image-3-tasks.md) > > List all Qwen Image 3.0 tasks > [card] [GET /v1/ai/text-to-image/qwen-image-3/\{task-id}](https://docs.magnific.com/api-reference/text-to-image/qwen-image-3/task-by-id.md) > > Get task status and results by ID ### Parameters | Parameter | Type | Required | Default | Description | | - | - | - | - | - | | `prompt` | `string` | Yes | - | Description of the image, or of the edit to apply (1-10,000 characters) | | `images` | `array` | No | - | Up to 3 images: public HTTPS URL, base64 string or upload id (`upl_...`). Without them the request is text-to-image | | `aspect_ratio` | `string` | No | `1:1` | `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3`, `1:2`, `2:1`, `4:5` | | `negative_prompt` | `string` | No | - | What to keep out of the image (up to 500 characters) | | `seed` | `integer` | No | random | 0 to 2147483647 | | `webhook_url` | `string` | No | - | URL for async status notifications | ### Output sizes About 1 megapixel, shaped to `aspect_ratio`. Measured examples: | `aspect_ratio` | Output | | - | - | | `1:1` | 1024x1024 | | `16:9` | 1344x768 | | `4:5` | 896x1152 | ## Frequently Asked Questions > [accordion] What is Qwen Image 3.0 and how does it work? > > Qwen Image 3.0 is Alibaba's image generation and editing model. You send a `prompt` (1-10,000 characters), optionally with up to 3 `images`, and receive a task ID immediately. Poll the task endpoint or configure a `webhook_url` to receive the image URL when processing completes. Each request generates one image. > [accordion] How do I edit an image? > > Send it in `images` and describe the change in the prompt, for example *"replace the sky in image 1 with a starry night; keep everything else unchanged"*. You can add up to two more images and name them by position (`image 2`, `image 3`). > [accordion] What image formats are supported? > > Common image formats as a public HTTPS URL, a base64-encoded string or an upload id (`upl_img_...`). Each image up to 10 MB, ideally 384 to 2048 px per side. Plain `http://` URLs are rejected. > [accordion] How much does Qwen Image 3.0 cost? > > The price is flat: one price per image. Input images, aspect ratio and the other parameters do not change it. See the [Pricing page](https://docs.magnific.com/pricing.md) for current rates. > [accordion] What is the difference between Qwen Image 3.0 and Qwen Image 3.0 Pro? > > They take the same parameters. [Qwen Image 3.0 Pro](https://docs.magnific.com/api-reference/text-to-image/qwen-image-3-pro/overview.md) is the higher quality tier and also renders at 2K (about 4 megapixels), priced by `resolution`. Qwen Image 3.0 renders at about 1 megapixel at a flat, lower price. > [accordion] What are the rate limits for Qwen Image 3.0? > > Rate limits depend on your subscription tier. See [Rate Limits](https://docs.magnific.com/ratelimits.md) for current limits. ## Best practices * **Name images by position**: Refer to inputs as `image 1`, `image 2`, `image 3` in the order you send them * **Say what stays**: In edits, describe the change and add *"keep everything else unchanged"* * **Use `negative_prompt`** to keep unwanted elements out instead of describing them in the prompt * **Production integration**: Use `webhook_url` instead of polling for scalable applications * **Error handling**: Implement retry logic with exponential backoff for 503 errors ## Related APIs * **[Qwen Image 3.0 Pro](https://docs.magnific.com/api-reference/text-to-image/qwen-image-3-pro/overview.md)**: The higher quality tier, at 1K or 2K * **[Ideogram 4.5](https://docs.magnific.com/api-reference/text-to-image/ideogram-4-5/overview.md)**: Image generation and editing with accurate text * **[Nano Banana Pro Flash](https://docs.magnific.com/api-reference/text-to-image/nano-banana-pro-flash/overview.md)**: Google's image generation and editing model This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.