Text-to-Image
Diffusers
English
360
360°
360-degree
360-image
equirectangular
equirectangular-projection
image-generation
Instructions to use ProGamerGov/qwen-360-diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ProGamerGov/qwen-360-diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ProGamerGov/qwen-360-diffusion", 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
- Draw Things
- DiffusionBee
q8 model grid artifacts
#4
by Izdis - opened
HI!
Using the qwen image 2512 Q8, still leads to some grid like artifacts.
Would you post a comfyUI workflow? Preferably for 24gb vram and less.
@Izdis The noise/error pattern of the 2512 Qwen Image model seems to have diverged slightly from the original Qwen Image model.
We are currently continuing the training of the qwen-360-diffusion-int8-bf16-v1.safetensorscheckpoint on Qwen Image 2512 to resolve any issues with artifacts.
@Izdis Our new Qwen Image 2512 version of the model has now be released, and you can find it in this repo under the name: 'qwen-360-diffusion-2512-int8-bf16-v2.safetensors'. It should hopefully resolve your issues!