Instructions to use YiYiXu/a2-diffusers-testing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use YiYiXu/a2-diffusers-testing with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("YiYiXu/a2-diffusers-testing", 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
-
Add modular_model_index.json for ModularPipeline.from_pretrained
Verified signatureae4c7ea
-
Write the real DPMSolverMultistep config
Verified signaturescheduler_config.json said `UniPCMultistepScheduler` while model_index.json said `DPMSolverMultistepScheduler`, so it loaded as DPM carrying UniPC's field set. The pipeline now samples with `self.scheduler` instead of constructing its own, so the file has to be correct. The resulting scheduler is bit-identical -- same timesteps, same sigmas -- to the one the old `flow_solver='dpm'` branch built.75f98d6
-
Add files using upload-large-folder tool
Verified signature86c2818 -
Add files using upload-large-folder tool
Verified signatureabde07c -
Upload vae/diffusion_pytorch_model.safetensors with huggingface_hub
Verified signaturea79b78e -
initial commit
Verified signature1068419