Instructions to use Hippotes/Gemma-4-ComfyUI-quants with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Hippotes/Gemma-4-ComfyUI-quants with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Hippotes/Gemma-4-ComfyUI-quants", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
ValueError: invalid tokenizer
#1
by MJS255 - opened
Trying to use these in text encoders I'm getting this error. The original ones from comfyui seem to work however π
Hmm weird, how are you using it?
With a simple clip load -> generate text -> preview text, it works fine
Tested again and it weirdly seems to just be that node. Works with generate text ty
MJS255 changed discussion status to closed
Probably the LTX node not handling int8 quantization as the native node does, thanks for the feedback π
