--- title: JoyAI-Image-Edit-ComfyUI canonical_url: "https://www.modelscope.ai/models/jd-opensource/JoyAI-Image-Edit-ComfyUI" md_url: "https://www.modelscope.ai/models/jd-opensource/JoyAI-Image-Edit-ComfyUI.md" repository: jd-opensource/JoyAI-Image-Edit-ComfyUI last_updated: 2026-07-29 license: apache-2.0 pipeline_tag: image-to-image tasks: - image-to-image base_model: - jdopensource/JoyAI-Image-Edit-Diffusers base_model_relation: finetune parameters: 50.2B tensor_type: - BF16 - U8 - F32 - I8 library_name: - safetensors - pytorch frameworks: - pytorch downloads: 177 stars: 0 tags: - comfyui - image-editing - joyai --- # JoyAI-Image-Edit-ComfyUI > JoyAI-Image-Edit-ComfyUI - An open-source model by jd-opensource on ModelScope. JoyAI-Image-Edit-ComfyUI jd-opensource/JoyAI-Image-Edit-ComfyUI is a 50.2B-parameter image-to-image model on ModelScope. licensed under apache-2.0. derived from jdopensource/JoyAI-Image-Edit-Diffusers. - **Repository**: jd-opensource/JoyAI-Image-Edit-ComfyUI - **License**: apache-2.0 - **Tasks**: image-to-image - **Parameters**: 50.2B - **Base model**: jdopensource/JoyAI-Image-Edit-Diffusers - **Tags**: comfyui, image-editing, joyai - **Downloads**: 177 - **Stars**: 0 - **Last updated**: 2026-07-29 Source: https://www.modelscope.ai/models/jd-opensource/JoyAI-Image-Edit-ComfyUI --- # JoyAI-Image-Edit-ComfyUI Repackaged model files for ComfyUI. Original model repository: https://huggingface.co/jdopensource/JoyAI-Image-Edit-Diffusers You can also use the same weight in: https://huggingface.co/Comfy-Org/JoyAI-Image-Edit Place the files in the following folders: ``` ComfyUI/ `-- models/ |-- diffusion_models/ | |-- joyai_image_edit_bf16.safetensors | `-- joyai_image_edit_int8_convrot.safetensors |-- text_encoders/ | |-- qwen3vl_8b_joyimage_edit_bf16.safetensors | `-- qwen3vl_8b_joyimage_edit_int8_convrot.safetensors `-- vae/ `-- wan_2.1_vae.safetensors ``` Download directly into `ComfyUI/models/`: ```bash hf download jdopensource/JoyAI-Image-Edit-ComfyUI \ --local-dir /path/to/ComfyUI/models ``` ![image](https://cdn-uploads.huggingface.co/production/uploads/67b58aebb57083505c88a074/BgOKEU-XfA2Twdw7d1uZM.png) Workflow: [workflow_joyimage_edit.json](workflow_joyimage_edit.json) ## Spatial Editing Reference JoyAI-Image supports three spatial editing prompt patterns: **Object Move**, **Object Rotation**, and **Camera Control**. For the most stable behavior, we recommend following the prompt templates below as closely as possible. For more information (including data curation and evaluation strategies), please refer to [SpatialEdit](https://github.com/EasonXiao-888/SpatialEdit). ### Object Move Use this pattern when you want to move a target object into a specified region. **Prompt template:** ```text Move the into the red box and finally remove the red box. ``` **Rules:** - Replace `` with a clear description of the target object to be moved. - The **red box** indicates the target destination in the image. - The phrase **"finally remove the red box"** means the guidance box should not appear in the final edited result. **Example:** ```text Move the apple into the red box and finally remove the red box. ``` ### Object Rotation Use this pattern when you want to rotate an object to a specific canonical view. **Prompt template:** ```text Rotate the to show the side view. ``` **Supported `` values:** ``` front, right, left, rear, front right, front left, rear right, rear left ``` **Rules:** - Replace `` with a clear description of the object to rotate. - Replace `` with one of the supported directions above. - This instruction is intended to change the **object orientation**, while keeping the object identity and surrounding scene as consistent as possible. **Examples:** ```text Rotate the chair to show the front side view. Rotate the car to show the rear left side view. ``` ### Camera Control Use this pattern when you want to change only the camera viewpoint while keeping the 3D scene itself unchanged. **Prompt template:** ```text Move the camera. - Camera rotation: Yaw {y_rotation}°, Pitch {p_rotation}°. - Camera zoom: in/out/unchanged. - Keep the 3D scene static; only change the viewpoint. ``` **Rules:** - `{y_rotation}` specifies the yaw rotation angle in degrees. - `{p_rotation}` specifies the pitch rotation angle in degrees. - `Camera zoom` must be one of: `in`, `out`,`unchanged` - The last line is important: it explicitly tells the model to preserve the 3D scene content and geometry, and only adjust the camera viewpoint. **Examples:** ```text Move the camera. - Camera rotation: Yaw 45°, Pitch 0°. - Camera zoom: in. - Keep the 3D scene static; only change the viewpoint. ``` ```text Move the camera. - Camera rotation: Yaw -90°, Pitch 20°. - Camera zoom: unchanged. - Keep the 3D scene static; only change the viewpoint. ``` ### Application **3D Reconstruction:** The first and third examples show point clouds with only a single given viewpoint. The second and fourth examples are augmented by [SpatialEdit](https://github.com/EasonXiao-888/SpatialEdit), which synthesizes richer spatial observations from the sparse input view. **Conditional-frames Based Video Generation:** Given the first frame, [SpatialEdit](https://github.com/EasonXiao-888/SpatialEdit) first generates the final frame of the video, and a video generation model then creates a smooth rotational transition between them while maintaining background consistency. ## Links - Source code and documentation: [github.com/jd-opensource/JoyAI-Image](https://github.com/jd-opensource/JoyAI-Image) - Original Diffusers-format weights: [jdopensource/JoyAI-Image-Edit-Diffusers](https://huggingface.co/jdopensource/JoyAI-Image-Edit-Diffusers) - Multi-image edit model for ComfyUI: [jdopensource/JoyAI-Image-Edit-Plus-ComfyUI](https://huggingface.co/jdopensource/JoyAI-Image-Edit-Plus-ComfyUI)