Instructions to use nitrosocke/redshift-diffusion-768 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nitrosocke/redshift-diffusion-768 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("nitrosocke/redshift-diffusion-768", 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
About redshift Model Training
#3
by AxonAxis - opened
I have experienced two versions of the redshift model and both of it are amazing. The results for model training are also very good. Would you please give more details about the specific settings of the model training parameters, such as the number of images in the training sets, the number of images in the classification sets, the ratio between the learning rate training steps training epochs, etc. Thank you