flux uncensored nf4 Summary Flux base model merged with uncensored LoRA, quantized to NF4. This model is not for those looking for "safe" or watered down outputs. It’s optimized for real world use with fewer constraints and lower VRAM requirements, thanks to NF4 quantization. Specs Model: Flux base LoRA: Uncensored version, merged directly Quantization: NF4 format for speed and VRAM efficiency Usage Not so much for plug and play model, but pretty straight forward (script from sayak [https://github.com/huggingface/diffusers/issues/9165 issue 2462431761]) Please install pip install U bitsandbytes to proceed. this README has what you'd need, it's a merge from Uncensored LoRA on CivitAI
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy