qwen-image/qwen-image-2512/lora
Create refined visuals from text with precise detail and flexible style control for design workflows.
This page is the text-to-image mode of the same compact Qwen stills model. Use Qwen Image 2.1 T2I here; image editing with references lives on a separate Edit page.
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
prompt* | Yes (*) | String | Example prompt | Up to 5,000 characters | Describe subject, setting, style, and any exact text. Quote wording to render it verbatim. |
aspect_ratio | No | String | 1:1 | 1:1, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16, 21:9, 9:21 | Output frame. Pixel size also depends on the resolution tier. |
resolution | No | String | 1K | 1K, 2K | 1K is faster; 2K has about four times the pixels and takes longer. |
background | No | String | opaque | opaque, transparent | transparent writes a real alpha channel. Describe only the subject. Cannot pair with JPEG. |
output_format | No | String | png | png, webp, jpeg | PNG and WebP can carry alpha. JPEG cannot, so it cannot be used with a transparent background. |
enhance_prompt | No | Boolean | true | true, false | Rewrites a short prompt into a fuller scene before generating. Turn off when the prompt is already exact. |
seed | No | Integer | -1 | -1 or 0–2147483647 | Fix a seed to reproduce a result; use -1 for a new variation. |
Qwen Image 2.1 T2I is billed by resolution: $0.020 per 1K image and $0.079 per 2K image. For a batch of 1–4 images, total cost is image count times the selected-tier rate.
Create refined visuals from text with precise detail and flexible style control for design workflows.
Turn written concepts into detailed visuals with precise image synthesis for creative teams.
AI image editing from text with region control and brand consistency.
Edit and fuse images into high quality results with Seedream 4.0.
Create photorealistic, text-accurate visuals with precise prompt control.
Precision-focused reference image editing for campaign artwork and polished product visuals.
Qwen Image 2.1 T2I turns a written prompt into a 1K or 2K still, including optional native transparency. It is a good fit for posters, product shots, stickers, and social frames that need readable type without a separate cutout step.
Yes. Set background to transparent so Qwen Image 2.1 T2I writes a real alpha channel, then choose PNG or WebP. Describe only the subject — mentioning a scene or floor often fills the background back in. JPEG cannot carry alpha.
Qwen Image 2.1 T2I offers a 1K or 2K detail tier and aspect ratios of 1:1, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16, 21:9, and 9:21. 1K is faster; 2K has about four times the pixels and takes longer. Check the current RunComfy parameter panel for the exact options.
The underlying model can edit images from references, but this Qwen Image 2.1 T2I page exposes only text-to-image. Use a prompt alone here; reference-image editing is handled on the Edit page of the same model.
Qwen Image 2.1 T2I can rewrite a short prompt into a fuller scene before generating; turn that off when the prompt is already exact. Set a fixed seed to reproduce a result, or use -1 for a new variation each run.
Yes. Prototype your prompt in the RunComfy model UI, then call the same Qwen Image 2.1 T2I model via the RunComfy HTTP API with identical parameters. You do not need to host or scale the model yourself.
Generations consume usd or credits. Qwen Image 2.1 T2I is billed at $0.020 per 1K image and $0.079 per 2K image. For a batch, multiply the selected-tier rate by the image count; new users typically get a free trial amount to test with.
Keep the prompt within 5,000 characters. Qwen Image 2.1 T2I follows concrete nouns, quoted on-image text, and a named layout more reliably than long mood boards. If a run misses a detail, shorten the brief and change one instruction at a time.
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.
