abenzerps/Qwen-Image-2.1-Uncensored-GGUF · Hugging Face

Source: https://huggingface.co/abenzerps/Qwen-Image-2.1-Uncensored-GGUF

**Notice regarding Q8_0:**Depending on your GPU and ComfyUI environment,qwen\-image\-2\.1\-Q8\_0\.ggufmight encounter a shape mismatch error (\[136\] vs \[128\]). Feel free to test it, but for guaranteed stability, we recommend usingQ4_K_M,Q5_K_M, orQ6_Kinstead. A patched Q8_0 file will be uploaded soon.

https://huggingface.co/abenzerps/Qwen-Image-2.1-Uncensored-GGUF#qwen-image-21-uncensored-ggufQwen-Image-2.1 Uncensored GGUF

GGUF quantizations ofQwen/Qwen-Image-2.1for local image generation using the original upstream base weights.

https://huggingface.co/abenzerps/Qwen-Image-2.1-Uncensored-GGUF#benchmarkBenchmark

https://huggingface.co/abenzerps/Qwen-Image-2.1-Uncensored-GGUF#gguf-filesGGUF files

Q4_K_Mis recommended for the best balance of size and quality.

https://huggingface.co/abenzerps/Qwen-Image-2.1-Uncensored-GGUF#text-encoders–vaeText Encoders & VAE

Companion model files packaged for ComfyUI:

https://huggingface.co/abenzerps/Qwen-Image-2.1-Uncensored-GGUF#usageUsage

Use the model withComfyUIandComfyUI-GGUF.

All required companion files (GGUF transformer, text encoder, and VAE) are hosted directly in this repository.

https://huggingface.co/abenzerps/Qwen-Image-2.1-Uncensored-GGUF#1-download–file-placement1. Download & File Placement

Download the files and place them in their respective ComfyUI directories:

ComfyUI/
└── models/
    ├── diffusion_models/
    │   └── qwen-image-2.1-Q4_K_M.gguf         # Choose one GGUF quantization (Q4_K_M recommended)
    ├── text_encoders/
    │   └── qwen3vl_8b_bf16.safetensors        # Or qwen3vl_8b_int8_convrot.safetensors (recommended for lower memory)
    └── vae/
        └── qwen_image_2.1_vae_bf16.safetensors

https://huggingface.co/abenzerps/Qwen-Image-2.1-Uncensored-GGUF#2-comfyui-setup2. ComfyUI Setup

1. Install ComfyUI-GGUF: Use the maintained fork with native Qwen-Image 2.1 support by cloningleejet/ComfyUI-GGUFinto your custom nodes:cd ComfyUI/custom_nodes git clone https://github.com/leejet/ComfyUI-GGUF (Note: If you have the oldercity96/ComfyUI\-GGUFinstalled and encounter anUnknown model architecture\!error, update to theleejetfork above or addModelQwenImagetotools/convert\.py).
2. Node Configuration:- Diffusion Model: Add the**Unet Loader \(GGUF\)node and select your downloaded\.gguffile. - Text Encoder: Add the standardCLIPLoadernode, selectqwen3vl\_8b\_bf16\.safetensors(orint8), and settypetoqwen\_image. - VAE: Add the standardVAELoader**node and selectqwen\_image\_2\.1\_vae\_bf16\.safetensors.
3. Official Workflows:- You can use the official Comfy-Org workflow templates:Text-to-ImageorImage Edit. - In the workflow, simply replace the defaultUNETLoadernode with**Unet Loader \(GGUF\)**.

https://huggingface.co/abenzerps/Qwen-Image-2.1-Uncensored-GGUF#memory–performance-notesMemory & Performance Notes

• Optimal Setup (GPU + RAM): Keep theGGUF diffusion model in GPU VRAM(where speed is crucial during sampling) and let thetext encoder run in / offload to System RAM (CPU). Because text encoding only runs once per prompt, this saves 9–17 GB of VRAM with virtually zero impact on generation speed.
• Recommended Configuration:- Diffusion:qwen\-image\-2\.1\-Q4\_K\_M\.gguf(~4.6 GB in VRAM) - Text Encoder:qwen3vl\_8b\_int8\_convrot\.safetensors(~9.35 GB in RAM)
• Low VRAM Mode: If you experience VRAM out-of-memory errors, start ComfyUI with the\-\-lowvramargument.

https://huggingface.co/abenzerps/Qwen-Image-2.1-Uncensored-GGUF#uncensoredUncensored

This GGUF release has no built-in safety checker or content filter. It generates adult, NSFW, and sensitive imagery directly without prompt refusals or blacked-out images. Output behavior depends solely on the input prompts and the environment in which the model is executed.

https://huggingface.co/abenzerps/Qwen-Image-2.1-Uncensored-GGUF#source-and-buildSource and build

• Source model:Qwen/Qwen-Image-2.1
• Text encoder & VAE source:Comfy-Org/Qwen-Image-2.1
• Source revision:b3179ad355be050328e483a9dfdd9e60cd62adfa
• Conversion:stable-diffusion.cppcommit1330cebae8f2ba99249df846cc0c9444fcbd4308
• **License:**Qwen Research License
• Checksums:SHA256SUMS