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
The color became dull.
After using this 4-step LoRa algorithm, the output video colors become somewhat darker. Do I need to adjust the LoRa weights or the number of steps? My current LoRa weights are 0.75 and the number of steps is 4.
All Turbo LoRAs work with a LoRA strength of 1.0.
After using this 4-step LoRa algorithm, the output video colors become somewhat darker. Do I need to adjust the LoRa weights or the number of steps? My current LoRa weights are 0.75 and the number of steps is 4.
Go with 0.5 and see. Also this Lora is version 0.1 which is telling by itself it is not a finished product by far. I mean it is proof of concept and should be treated as such.
After using this 4-step LoRa algorithm, the output video colors become somewhat darker. Do I need to adjust the LoRa weights or the number of steps? My current LoRa weights are 0.75 and the number of steps is 4.
Go with 0.5 and see. Also this Lora is version 0.1 which is telling by itself it is not a finished product by far. I mean it is proof of concept and should be treated as such.
All Turbo LoRAs work with a LoRA strength of 1.0.
All Turbo LoRAs work with a LoRA strength of 1.0.
No they do not. Go ask larry what strength to use his lora at.
All Turbo LoRAs work with a LoRA strength of 1.0.
No they do not. Go ask larry what strength to use his lora at.
He clearly states that the colors are dark. Using Turbo LoRAs at low power causes the colors to become darker. Using them at high power, on the other hand, causes the colors to blow out. Excessive color blowout is common with Turbo LoRAs, so many people don’t even use them. Turbo LoRAs are used at strength 1.0. If you claim otherwise, you need to show an example Turbo LoRA.