Instructions to use IsaacAkintaro/class_conditioned_training_output with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use IsaacAkintaro/class_conditioned_training_output with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("IsaacAkintaro/class_conditioned_training_output", 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
Download training_metrics.csv from IsaacAkintaro/class_conditioned_training_output: direct link, hf CLI and curl.
- Browser
- Download file 255 Bytes
-
https://huggingface.co/IsaacAkintaro/class_conditioned_training_output/resolve/main/training_metrics.csv
- Command line
-
hf download hf://IsaacAkintaro/class_conditioned_training_output/training_metrics.csv
-
curl -L -o training_metrics.csv https://huggingface.co/IsaacAkintaro/class_conditioned_training_output/resolve/main/training_metrics.csv
255 Bytes
| epoch,train_loss,val_loss,learning_rate,psnr,ssim,lpips | |
| 1,0.7206861972808838,0.7251554819253775,1.02e-05,14.525068553193073,0.09988017,1.0393900045981774 | |
| 2,0.10780823230743408,0.1385885666196163,2.04e-05,16.468041622585694,0.31178284,0.715363873885228 | |