Text-to-Image
Diffusers
Safetensors
GGUF
lora
image-to-image
image-editing
distillation
turbo
few-step
qwen-image
comfyui
int8
fp8
quantized
Instructions to use Viggle/Qwen-Image-2.1-viggle-turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Viggle/Qwen-Image-2.1-viggle-turbo with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image-2.1", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Viggle/Qwen-Image-2.1-viggle-turbo") 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
Tested and working great
#2
by NeonSparks - opened
Thanks for this! Just tested on T2I and its working great, for anime prompts it actually makes the images better for some reason?
I think mostly it's the distillation that make images sharper (but diversity reduced)