Qwen Edit Any Pose

Qwen Edit Any Pose

Changes the pose of a person in a picture in your browser using Qwen image edit 2511 with an AnyPose LoRA. Suits designers, illustrators and developers trying pose editing.

Made by rl74 on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: This Space is a browser demo of pose editing. It combines the Qwen image edit 2511 model with an AnyPose LoRA, a small add-on that teaches the model to move a subject into a new pose. The page runs on Hugging Face hardware, so nothing needs installing.

Who it suits: It suits designers, illustrators and hobbyists who want to try changing a pose in a picture. Developers can read a short app that stacks Qwen image edit with a pose LoRA.

Industry | Who uses it | How they use it | Example
Design | Graphic designers | Try new poses on a character or model picture | Move a standing figure into a different stance
Illustration | Artists | Test a pose idea on a reference image | Start from a sample picture in the repository
E-commerce | Shop owners | Preview a model photo in another pose | Try a different posture on a product shot
Software | Developers | Read an app that combines a LoRA and a Lightning build | Open app.py and optimization.py

You can skip it if you need exact, repeatable poses from a skeleton, since this is an image-based model demo.

Where to use it:

• A web browser: open the Space page on Hugging Face
• Windows, macOS or Linux: run a copy with Python
• An MCP client: the Space carries an MCP tag on Hugging Face

Use case | Who | What they get back
Change a pose | Designers | The picture with the subject in a new pose
Test on samples | Newcomers | Results from the sample pictures that ship with it
Run your own copy | Developers | The same app on your own computer

How to set it up: The online page needs nothing. A local copy needs Python and the packages in requirements.txt.

• A web browser for the online demo
• Python for a local copy
• The packages listed in requirements.txt

1. To use it online, open the Space page on Hugging Face.
2. To run a copy, install the Hugging Face hub package.
3. Download the Space into a local folder.
4. Move into the folder and install Gradio 6.2.0 and the listed packages.
5. Start the app.

pip install -U huggingface_hub
pip install gradio==6.2.0
pip install -r requirements.txt
python app.py

Put your own value in its key setting first.

How to use it: Start the app from its folder, or open the Space online. Add a picture of a person, give the pose you want or a reference, and generate. The repository includes a few sample pictures to try first.

python app.py

Example: You load one of the sample pictures and ask for a new pose. The page returns the same subject in the new pose, and you can try again with different wording.

For newcomers and experts: If you are new to this, begin with a sample picture and a simple pose change. Check the result against the original before trying your own photos.

If you know the field, the app uses the Qwen image edit 2511 base with the AnyPose LoRA. It also names a Lightning build of 2511, the 2509 edit model and a flash-attention kernel package. A file named optimization.py sits next to the app, and the hosted Space runs on zero-a10g hardware.

You add a picture and a pose request
The Gradio app loads Qwen edit with AnyPose
The model redraws the subject
You get the edited picture

Good to know: The README gives only a tagline, so the page and app.py hold the real details. The adapters are third-party files with their own terms.

• License: apache-2
• Cost to run: none named
• Data it reaches: the pictures and text you give it

On Hugging Face, 13 November 2026

• Likes: 5
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/rl74/Qwen-Image-Edit-2511-AnyPose
• Files: https://huggingface.co/spaces/rl74/Qwen-Image-Edit-2511-AnyPose/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.