Instructions to use Jingya/pixart_sigma_pipe_xl_2_512_ms with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Jingya/pixart_sigma_pipe_xl_2_512_ms with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Jingya/pixart_sigma_pipe_xl_2_512_ms", 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
This repo gathers all components in a Pixart Sigma pipeline:
Transformer: PixArt-alpha/PixArt-Sigma-XL-2-512-MS
Other components: PixArt-alpha/pixart_sigma_sdxlvae_T5_diffusers
This is for ease the test of Optimum Neuron's Pixart support, please do not use it for other purposes.
- Downloads last month
- 2