Qwen-Image-Edit 2511 GGUF (Turbo LoRA + NSFW LoRA baked-in)
A pre-merged, quantized build of Qwen-Image-Edit-2511 with two fine-tunes baked into the weights:
- Turbo (Lightning 4-step)
- NSFW Lora
Sample Turbo Edit (8-steps)
A standard edit showing the base capability is intact:
Sample Image-to-Image (4-steps)
Image-to-Image works and is very fast:
- Note: "Editing" is not this models strength, the model needs further tuning for stronger NSFW edits.
Sample Text-to-Image (4-steps)
The highlight of this model. Fast and uncensored.
- Note: Guardrails are in place to prevent illegal content, but mostly NSFW.
Components used to generate
| Component | File | ~Size | Download |
|---|---|---|---|
| Transformer | qwen-image-edit-2511-uncensored-Q4_K_M.gguf | 11.7 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 | Notes |
|---|---|---|
| Resolution | 1024 × 1024 | 512x512 min |
| Steps | 4 | 4-steps min, 16-steps max |
| CFG | 1.0 | always use 1.0 for turbo variants |
⚠ Must use the updated GGUF Loader ⚠
In comfy:
- Open the ComfyUI Manager
- Change the channel to "Channel (remote)"
- and search for comfyui-gguf-loader
Use the workflow Link
