Downloads · 30 days
58
3% of all-time downloads
FLUX.1-dev-bf16-gguf
mo137/FLUX.1-dev-bf16-gguf
FLUX.1-dev-bf16-gguf is a text-to-image model from mo137. Use it when you need an image from a text prompt. It is set up for gguf. The card lists the license as other.
Flux.1-dev in bfloat16, exactly the same tensors as in black-forest-labs' original safetensors. AFAIK no inference software supports bf16 FLUX yet, but maybe this file can help. I have no clue if it would improve anyt…
All-time downloads
2.1K
Public
Repo size
23.8 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.gguf23.8 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- gguf
- License
- other
- Access
- Public
- Created
- Aug 22, 2024
- Updated
- Aug 24, 2024
- SHA
- 0cf51939
Base models
Model card
From the Hugging Face model README
⚠️ bf16 GGUF Flux is not yet supported by any UI like ComfyUI or Forge! ⚠️
Flux.1-dev in bfloat16, exactly the same tensors as in black-forest-labs' original safetensors. AFAIK no inference software supports bf16 FLUX yet, but maybe this file can help. I have no clue if it would improve anything, but bf16 –> fp16 conversion is lossy, so... maybe?
This is a direct GGUF conversion of black-forest-labs/FLUX.1-dev
As this is a quantized model not a finetune, all the same restrictions/original license terms still apply.
The model files can be used with the ComfyUI-GGUF custom node.
Place model files in ComfyUI/models/unet - see the GitHub readme for further install instructions.
Please refer to this chart for a basic overview of quantization types.
(Model card mostly copied from city96/FLUX.1-dev-gguf - which contains conventional and useful GGUF files.)
- Task
- Text-to-Image
- Library
- gguf
- License
- other
- Created
- Aug 22, 2024
- Updated
- Aug 24, 2024