Qwen-Image-Edit 2509 GGUF (Turbo LoRA + Multiple-Angles LoRA baked-in)
A pre-merged, quantized build of Qwen-Image-Edit-2509 with two fine-tunes baked into the weights:
- Turbo (Lightning 8-step V2.0)
- Multiple-Angles
Sample Turbo Edit (8-steps)
A standard edit showing the base capability is intact:
Sample Multi Angle (12-steps)
Components used to generate
| Component | File | ~Size | Download |
|---|---|---|---|
| Transformer | qwen-image-edit-2509-turbo-multiple-angles-Q6_K.gguf | 11.4 GB | Link |
| Text Encoder | Qwen2.5-VL-7B-Instruct-q4_0.gguf | 4.43 GB | Link |
| mmproj | Qwen2.5-VL-7B-Instruct-mmproj-f16.gguf | 1.35 GB | Link |
| VAE | qwen_image_vae.safetensors | 254 MB | Link |
Sample settings
| Parameter | Value |
|---|---|
| Resolution | 1024 × 1024 |
| Steps | 12 |
| CFG | 1.0 |
| Seed | 42 |
⚠ Must use the updated GGUF Loader ⚠
In comfy:
- Open the ComfyUI Manager
- Change the channel to "Channel (remote)"
- and search for comfyui-gguf-loader

Sources
- Base: Qwen/Qwen-Image-Edit-2509 (Apache-2.0)
- Turbo LoRA: Qwen-Image-Lightning-8steps-V2.0
- Multiple-angles LoRA: qwen-image-edit-2509-Multiple-angles.safetensors
- GGUF tooling: llama.cpp (
llama-quantize),ggufPython package