Instructions to use tianweiy/DMD2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use tianweiy/DMD2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("tianweiy/DMD2", 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
what samplers to use other than lcm ?
#3
by pikkaa - opened
what samplers i can use with DMD2 ? other than lcm ?
in comfyui there's recommended scheduler ?
Euler A works well. I usually generate with LCM then upscale with Eular A Karras to add details.
Kohaku_LoNyu_Yog works well if I remember correctly, from https://github.com/Koishi-Star/Euler-Smea-Dyn-Sampler