Spaces:
Running on Zero
Running on Zero
| title: JoyAI Image Edit Plus | |
| emoji: 🎨 | |
| colorFrom: indigo | |
| colorTo: green | |
| sdk: gradio | |
| sdk_version: 6.15.1 | |
| app_file: app.py | |
| short_description: Multi-image instruction-guided image editing | |
| python_version: "3.12" | |
| startup_duration_timeout: 1h | |
| JoyAI-Image Edit Plus is a multi-image instruction-guided editing model from the JoyAI-Image family. | |
| Provide one or more reference images and a text instruction to generate a new image that combines | |
| elements from the references according to the instruction. | |
| ## Model | |
| - **Model**: [jdopensource/JoyAI-Image-Edit-Plus-Diffusers](https://huggingface.co/jdopensource/JoyAI-Image-Edit-Plus-Diffusers) | |
| - **Architecture**: Qwen3-VL-8B text encoder + JoyImageEditPlusTransformer3D (16B) + AutoencoderKLWan VAE | |
| - **License**: Apache-2.0 | |
| ## How it works | |
| 1. Upload 1–6 reference images in the gallery. | |
| 2. Write an instruction describing how to combine or edit the images. | |
| 3. The model generates a new image that follows your instruction using the references as context. |