Multi-image editing support
According to the model card, the September iteration adds multi-image editing trained via image concatenation, with best performance on 1 to 3 inputs.
Open Source Model Profile · Qwen
Qwen-Image-Edit-2509
Qwen-Image-Edit-2509 is a 20.43B-parameter image-editing model from Qwen. According to the model card, it adds multi-image editing and improved consistency over the August release.
- Publisher
- Qwen
- Task
- image-to-image
- Model type
- Unknown
- License
- apache-2.0
- Library
- diffusers
- Publication status
- Approved for indexing
Model overview
Qwen-Image-Edit-2509 is published by Qwen as an image-to-image model. Safetensors metadata reports 20,430,401,088 parameters. According to the model card, it is the September monthly iteration of Qwen-Image-Edit with multi-image editing and stronger single-image consistency.
Recorded capabilities
Single-image consistency improvements
According to the model card, single-image editing improves person, product, and text consistency, including fonts, colors, and materials.
Native ControlNet support
According to the model card, the model natively supports ControlNet conditions including depth, edge, and keypoint maps.
20.43B model with Diffusers
Safetensors metadata reports 20,430,401,088 parameters, and the card documents QwenImageEditPlusPipeline Diffusers usage.
Use cases in the source record
- Multi-image editing workflows combining inputs such as person plus person, product, or scene with text prompts.
- Single-image editing for portraits, product posters, and text edits, including ControlNet-conditioned edits with depth, edge, or keypoint maps.
Limitations and unknowns
- No evaluation results were extracted from this record.
- Provider state is historical snapshot data, not independently refreshed current availability.
- Capability and improvement information comes from the publisher model card and has not been independently verified by Ethen.
Source and provenance
Source: Qwen/Qwen-Image-Edit-2509
Captured: Unknown. Processed: 2026-09-07T19:34:35.839662+00:00.
💜 Qwen Chat | 🤗 Hugging Face | 🤖 ModelScope | 📑 Tech Report | 📑 Blog 🖥️ Demo | 💬 WeChat (微信) | 🫨 Discord | Github Introduction This September, we are pleased to introduce Qwen-Image-Edit-2509, the monthly iteration of Qwen-Image-Edit. To experience the latest model, please visit Qwen Chat and select the "Image Editing" feature. Compared with Qwen-Image-Edit released in August, the main improvements of Qwen-Image-Edit-2509 include: Multi-image Editing Support : For multi-image inputs, Qwen-Image-Edit-2509 builds upon the Qwen-Image-Edit architecture and is further trained via image concatenation to enable multi-image editing.…
F001F002F003F004F005F006F008F009F010F011F012F013F014