Instructions to use mann-e/Mann-E_Art with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use mann-e/Mann-E_Art with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("mann-e/Mann-E_Art", 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
Do you have a lightweight version? Is FP16 version supported
#2
by michaelj - opened
Do you have a lightweight version? Is FP16 version supported
FP16 is supported.
FP16 is supported.
The character transformations generated by him are prone to deformation, such as three hands, three legs, distorted fingers or faces. Is there a way to solve this problem