Instructions to use amd/Nitro-E with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use amd/Nitro-E with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("amd/Nitro-E", 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
img2img?
#2
by ztsvvstz - opened
Really interested in using this artistically. Is there an img2img mode or a way to pass custom latents?
It would be more interesting if it were a unified model in a GGUF file. It's not very practical to use it in its current form.