Instructions to use dg845/consistency-model-pipelines with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use dg845/consistency-model-pipelines with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("dg845/consistency-model-pipelines", 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
Commit History
-
Upload new cd_imagenet64_l2 unet checkpoint (fix mid block attention group norm bug)
e8fb2ac -
Delete unet
Remove unet (fix mid block attention group norm bug)8ce6c13 -
Delete scheduler
Remove scheduler ((fix mid block attention group norm bug)526dd24 -
Delete model_index.json
Remove model_index.json (fix mid block attention group norm bug)c09daea
-
Update README.md
Fix typosdd6eaad -
Update README.md
Add draft model card for diffusers cd_imagenet64_l2 consistency model checkpoint.9f8c855
-
Upload 4 files
Upload new diffusers consistency model cd_imagenet64_l2 checkpoint (apply attention weight fix and scheduler changes)f8c4726 -
Delete unet
Remove unet (apply attention weight fix and scheduler changes)acbdcd8 -
Delete scheduler
Remove scheduler (apply attention weight fix and scheduler changes)2279ba5 -
Delete model_index.json
Remove model_index.json (apply attention weight fix and scheduler changes)e8256ec
-
Upload 4 files
Reupload cd_imagenet64_l2 pipeline (DiffusionPipeline.save_pretrained doesn't support subfolder argument)506a616 -
Delete cd_imagenet64_l2
Remove directory (DiffusionPipeline.save_pretrained doesn't support subfolder argument)c43c53c -
Upload 4 files
Add diffusers version of a Consistency Distillation consistency model distilled on the ImageNet-64 dataset (cd_imagenet64_l2.pt in the original release).638c061 -
initial commit
40d3bb5