Instructions to use abenzerps/Qwen-Image-2.1-Uncensored-Quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use abenzerps/Qwen-Image-2.1-Uncensored-Quantized with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download abenzerps/Qwen-Image-2.1-Uncensored-Quantized --local-dir Qwen-Image-2.1-Uncensored-Quantized
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Commit History
21 days ago
-
FP8 updated: Fix ComfyUI quantization metadata
Verified signatureAdded missing comfy_quant tensors, _quantization_metadata header, and scaled_fp8 marker so ComfyUI recognizes the model as scaled FP8 (MixedPrecisionOps), resolving the blank/black output issue.40319fb -
INT8 support added.
Verified signature26fee66 -
FP8 support added.
Verified signature3100d25
22 days ago
-
Initial release: Qwen-Image-Uncensored-2.1 GGUF
1206d38