gguf quantized version of flux-dev (incl. gguf encoder and gguf vae)

  • drag flux-dev to > ./ComfyUI/models/diffusion_models
  • drag clip-l, t5xxl to > ./ComfyUI/models/text_encoders
  • drag vae to > ./ComfyUI/models/vae
  • drag demo picture (below) to > your browser for workflow
Prompt
cute anime girl with massive fluffy fennec ears and a big fluffy tail blonde messy long hair blue eyes wearing a maid outfit with a long black gold leaf pattern dress and a white apron mouth open holding a fancy black forest cake with candles on top in the kitchen of an old dark Victorian mansion lit by candlelight with a bright window to the foggy forest and very expensive stuff everywhere
Prompt
cute anime girl with massive fluffy fennec ears and a big fluffy tail blonde messy long hair blue eyes wearing a maid outfit with a long black gold leaf pattern dress and a white apron mouth open holding a fancy black forest cake with candles on top in the kitchen of an old dark Victorian mansion lit by candlelight with a bright window to the foggy forest and very expensive stuff everywhere
Prompt
cute anime girl with massive fluffy fennec ears and a big fluffy tail blonde messy long hair blue eyes wearing a maid outfit with a long black gold leaf pattern dress and a white apron mouth open holding a fancy black forest cake with candles on top in the kitchen of an old dark Victorian mansion lit by candlelight with a bright window to the foggy forest and very expensive stuff everywhere

major upgrade

  • revised version; load faster than before with full set gguf (model + encoder + decoder)
  • upgraded model to fp32; similar file size; shorten loading time; significant difference
  • upgraded encoder and decoder to fp32; same file size; better quality

screenshot

reference

Downloads last month
192
GGUF
Model size
123M params
Architecture
pig

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Examples
Examples
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for calcuis/flux-dev-gguf

Quantized
(1)
this model