Instructions to use hf-internal-testing/tiny-pika-h3-flex-modular-pipe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use hf-internal-testing/tiny-pika-h3-flex-modular-pipe with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("hf-internal-testing/tiny-pika-h3-flex-modular-pipe", 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
Use MiniMaxH3Scheduler with stochastic sampling for the two schedulers
#2
by YiYiXu HF Staff - opened
Pika H3 Flex's sampler is MiniMaxH3Scheduler with stochastic_sampling and shift_provided_sigmas; the six-step schedule moves to the pipeline config.
YiYiXu changed pull request status to merged