README.md

metadata

base_model:
  - Wan-AI/Wan2.2-TI2V-5B-Diffusers
  - Efficient-Large-Model/LongLive-2.0-5B
pipeline_tag: text-to-video
tags:
  - sglang
  - longlive
  - autoregressive
  - video-generation

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 generator weights extracted from the original model_bf16.pt, kept in their original (model.*) naming; SGLang's LongLive2Transformer3DModel.param_names_mapping maps 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