How to use calcuis/qwen-image-gguf with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("calcuis/qwen-image-gguf", dtype=torch.bfloat16, device_map="cuda") prompt = "cute anime girl with massive fennec ears and a big fluffy fox tail with long wavy blonde hair between eyes and large blue eyes blonde colored eyelashes chubby wearing oversized clothes summer uniform long blue maxi skirt muddy clothes happy sitting on the side of the road in a run down dark gritty cyberpunk city with neon and a crumbling skyscraper in the rain at night while dipping her feet in a river of water she is holding a sign that says \"ComfyUI is the best\" written in cursive" image = pipe(prompt).images[0]
Is there any way to use these quants in ComfyUI?I get an error "This text model is incompatible with llama.cpp!" when trying.I use city96/ComfyUI-GGUF custom node
it works with gguf-node (pypi|repo|pack); that's pig quant
· Sign up or log in to comment
