ComfyUI Node: HF Transformers load model
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
huggingface-transformers
Inputs
model_class STRING
pretrained_model_name_or_path STRING
subfolder STRING
device
- default
- auto
- cpu
dtype
- default
- float32
- bfloat16
- float16
- bitsandbytes_8bit
- bitsandbytes_4bit
kwargs STRING
Outputs
HFT_MODEL
Extension: ComfyUI-HF-Diffusers
A lot of custom nodes for ComfyUI are really just bindings to HuggingFace Diffusers and/or Transformers, but overly constrained to use them in very particular ways.
Authored by Yahweasel
Looking for a different node?
More nodes in ComfyUI-HF-Diffusers
- HF Diffusers load AutoencoderKL (VAE)
- HF Diffusers encode prompt
- HF Diffusers load LoRA
- HF Diffusers load pipeline
- HF Diffusers run pipeline
- HF Diffusers VAE decode
- HF Diffusers VAE encode
- HF Transformers create conversation
- HF Transformers load pipeline
- HF Transformers run pipeline
- HF Transformers unpack conversation
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.