Downloads · 30 days
32.5K
35% of all-time downloads
Qwen-Image-2.1-Uncensored-GGUF
0xSojalSec/Qwen-Image-2.1-Uncensored-GGUF
Qwen-Image-2.1-Uncensored-GGUF is a text-to-image model from 0xSojalSec. Use it when you need an image from a text prompt. It is set up for gguf. The card lists the license as other.
GGUF quantizations of Qwen/Qwen-Image-2.1 for local image generation using the original upstream base weights.
All-time downloads
94K
Public
Repo size
27.3 GB
Likes
92
Trending 2
Repo makeup
Click a slice to open those files.
.gguf27.3 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- gguf
- License
- other
- Access
- Public
- Created
- Sep 20, 2026
- Updated
- Sep 20, 2026
- SHA
- 242be4d1
Base models
Model card
From the Hugging Face model README
Qwen-Image-2.1 Uncensored GGUF
GGUF quantizations of Qwen/Qwen-Image-2.1 for local image generation using the original upstream base weights.
Benchmark
GGUF files
| Quantization | File | Size |
|---|---|---|
| Q8_0 | qwen-image-2.1-Q8_0.gguf | 7.59 GiB |
| Q6_K | qwen-image-2.1-Q6_K.gguf | 5.88 GiB |
| Q5_K_M | qwen-image-2.1-Q5_K_M.gguf | 5.22 GiB |
| Q4_K_M | qwen-image-2.1-Q4_K_M.gguf | 4.6 GiB |
| Q4_0 | qwen-image-2.1-Q4_0.gguf | 4.05 GiB |
Q4_K_M is recommended for the best balance of size and quality.
Usage
Use the model with ComfyUI and ComfyUI-GGUF.
These GGUF files contain the Qwen-Image-2.1 image transformer; the original text encoder and VAE are also required for inference.
- Download one GGUF file from this repository.
- Place it in the ComfyUI diffusion models directory.
- Download the required text encoder and VAE from Qwen/Qwen-Image-2.1.
- Place them in their corresponding ComfyUI model directories.
- Load a Qwen-Image-2.1 workflow and select the GGUF model.
ComfyUI/
└── models/
├── diffusion_models/
│ └── qwen-image-2.1-Q4_K_M.gguf
├── text_encoders/
│ └── ...
└── vae/
└── ...
Uncensored
These are quantizations of the original Qwen-Image-2.1 weights; no fine-tuning, abliteration, or other weight modification was applied. Local testing found no pipeline-level safety checker or prompt blacklist, and the model generated the tested adult, nudity, violence, and other sensitive categories without observed runtime refusal. Hosted services may apply their own moderation.
Source and build
- Source model: Qwen/Qwen-Image-2.1
- Source revision:
b3179ad355be050328e483a9dfdd9e60cd62adfa - Conversion: stable-diffusion.cpp commit
1330cebae8f2ba99249df846cc0c9444fcbd4308 - License: Qwen Research License
- Checksums: SHA256SUMS
- Task
- Text-to-Image
- Library
- gguf
- License
- other
- Created
- Sep 20, 2026
- Updated
- Sep 20, 2026