import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("GG2024/LongCat-Video-Avatar-1.5-INT8-runtime", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]LongCat Video Avatar 1.5 INT8 runtime subset
This repository contains only the files required by the RunPod INT8
two-speaker worker. The files are redistributed from the MIT-licensed
meituan-longcat/LongCat-Video
at 03b55529b1d1d4045f5fbe14d65c8c6e8116b278 and
meituan-longcat/LongCat-Video-Avatar-1.5
at 92016c71d5d318d0f5d84e4db30015a571484ab6.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support