MiniMax-H3-Lightx2v
Collection
5 items β’ Updated β’ 11
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")MiniMax-H3 Turbo
Please check our repository or the LightX2V MiniMax-H3 examples to reproduce the results.
Please check the model specifications for more details.
Online App
Try the MiniMax-H3 Turbo LoRA directly in LightX2V Studio:
- LightX2V Studio: x2v.light-ai.top
The Studio currently uses the FL2V 8-step v1.0 768p LoRA, which provides improved video and audio generation quality with 8-step inference.
The model version deployed in the Studio may be updated over time.
Studio Preview
Online API
Integrate MiniMax-H3 Turbo into your application through the LightX2V API:
- API Documentation: x2v.light-ai.top/api-docs
- Downloads last month
- 925,400
Model tree for lightx2v/Minimax-h3-Turbo
Base model
MiniMaxAI/MiniMax-H3