Text-to-Video
Diffusers
Safetensors
LongLive2Pipeline
sglang
longlive
autoregressive
video-generation
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Rabinovich/LongLive-2.0-5B-Diffusers", torch_dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]LongLive-2.0-5B (Diffusers-format, for SGLang Diffusion)
A diffusers-directory-layout repackaging of Efficient-Large-Model/LongLive-2.0-5B
so it loads directly in SGLang Diffusion (sglang.multimodal_gen) without any runtime overlay/materialization.
- transformer/ — the
generatorweights extracted from the originalmodel_bf16.pt, kept in their original (model.*) naming; SGLang'sLongLive2Transformer3DModel.param_names_mappingmaps them to the diffusers module names at load (same convention as LingBot-World). - scheduler / text_encoder / tokenizer / vae — taken from
Wan-AI/Wan2.2-TI2V-5B-Diffusers. model_index.json_class_name = LongLive2Pipeline.
Usage (SGLang)
sglang generate --model-path Rabinovich/LongLive-2.0-5B-Diffusers \
--prompt "A compact silver robot walks through a clean robotics lab." \
--num-frames 61 --height 480 --width 832 --num-inference-steps 4 --save-output
Original model & method: NVlabs/LongLive. License: NVIDIA Open Model License
- Downloads last month
- 2,785
Model tree for Rabinovich/LongLive-2.0-5B-Diffusers
Base model
Efficient-Large-Model/LongLive-2.0-5B