Instructions to use lightx2v/Minimax-h3-Turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lightx2v/Minimax-h3-Turbo with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("lightx2v/Minimax-h3-Turbo", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
PEFT Training Params
#8
by QrusherZA - opened
Hi, there is no documentation on the PEFT parameters, what was the alpha used for this one?
Hi, there is no documentation on the PEFT parameters, what was the alpha used for this one?
Hi, it's 8. https://github.com/ModelTC/Minimax-H3-Turbo/blob/main/inference_minimax_h3.py#L408
Sorry for the inconvenience.
Awesome thanks much, Nah no inconvenience at all, wanted to make a comfyui conversion but using kijai one now, I think he baked 16, so will try that at half STR and test