Text-to-Image
Diffusers
Safetensors
image-to-image
quantization
w4a4
svdquant
gptq
nunchaku
8-bit precision
Instructions to use ModelsLab/Qwen-Image-2.1-W4A4-int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ModelsLab/Qwen-Image-2.1-W4A4-int4 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ModelsLab/Qwen-Image-2.1-W4A4-int4", 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
- Local Apps Settings
- Draw Things
- DiffusionBee
Any recipe for vLLM?
#1
by hdnh2006 - opened
Hello!
Thanks for this fantastic release, any idea how to deploy it in 24GB of VRAM using vLLM omni? is this even possible?
Thanks in advance.
vLLM omni won't support this format, use custom code stack, we have in readme, it will work. or better ask claude to make it work, it will work.