Sign in to use the playground
Run this model with your Chutes account, quota, and API access.
Model facts & API quick start
Qwen-Image-Edit-2511 is served on Chutes inside a Trusted Execution Environment (TEE). Call it at https://vonkaiser-qwen-image-edit-2511.chutes.ai/generate with a Chutes API key.
Qwen-Image-Edit-2511 at a glance
- Model ID
Qwen-Image-Edit-2511- Developer
- Qwen
- Deployed by
- vonkaiser
- Type
- Image
- Compute price
- $2.25 per hour
- Modalities
- text, image in → image out
- Confidential compute (TEE)
- Yes, runs in a Trusted Execution Environment
- Open weights
Qwen/Qwen-Image-Edit-2511- Architecture
- QwenImageTransformer2DModel diffusion transformer (60 layers, 24 heads, head dim 128) with a Qwen vision-language text encoder; diffusers QwenImageEditPlusPipeline
- License
- Apache-2.0
- Released
- 2025-12
- Task
- Instruction-based image editing (image-to-image)
- Reference images
- 1-3 input images per request on this chute
- Languages
- English and Chinese editing instructions
- Improvements over 2509
- Reduced image drift, better character and multi-person consistency, built-in popular LoRA effects, industrial design and geometric reasoning (per model card)
- Output format on Chutes
- image/jpeg
API quick start
- Base URL
https://vonkaiser-qwen-image-edit-2511.chutes.ai- Endpoint
POST /generate- Auth header
Authorization: Bearer $CHUTES_API_KEY
# NOTE: replace the image_b64s placeholder(s) with real base64 data first.
curl -X POST "https://vonkaiser-qwen-image-edit-2511.chutes.ai/generate" \
-H "Authorization: Bearer $CHUTES_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "a serene mountain lake at sunset",
"seed": 42,
"width": 1024,
"height": 1024,
"image_b64s": [
"<base64-encoded image>"
],
"true_cfg_scale": 1,
"negative_prompt": "",
"num_inference_steps": 4
}' \
--output output.jpgQwen-Image-Edit-2511 FAQ
How many input images can I send?
One to three reference images per request, as raw base64 strings in the image_b64s array. Multi-image input is how you compose subjects from separate photos, such as merging two portraits into one group shot.
Why does the chute default to 4 steps when the model card uses 40?
The chute is configured as a low-latency serving profile: 4 inference steps with true_cfg_scale 1. The model card's example uses 40 steps with true_cfg_scale 4.0. Both fields are request parameters, so you can raise them for higher-fidelity edits at the cost of latency and compute.
Does it keep the parts of the image I didn't ask to change?
That is the design goal, and the 2511 release specifically targets reduced image drift and improved consistency versus 2509. It is still a generative model, though: the whole frame is regenerated, so untouched regions are visually preserved rather than byte-identical.
What license is Qwen-Image-Edit-2511 under?
Apache-2.0, per the model card's license section and the Hugging Face repo metadata. Commercial use, modification, and redistribution are permitted under standard Apache terms.
Can I write edit instructions in Chinese?
Yes. The model is trained for English and Chinese instructions, and the model card demonstrates bilingual editing.
How do I call it from code?
POST flat JSON to https://vonkaiser-qwen-image-edit-2511.chutes.ai/generate with an Authorization: Bearer header. Base64-encode your input image(s) into image_b64s, set prompt to the edit instruction, and save the response body as a JPEG.
Is this a text-to-image model?
No, it is an editing model: it expects at least one reference image and an instruction describing the change. For generation from scratch use a text-to-image chute such as Qwen-Image-2512 or Z-Image Turbo.