Skip to content
ModelVerifiedExternal
Browse files

LongLive 2.0 5B Diffusers

A diffusers-directory-layout repackaging of Efficient-Large-Model/LongLive-2.0-5B so it loads directly in SGLang Diffusion (sglang.multimodalgen) without any runtime overlay/materialization.

Sourcehuggingface.co/Rabinovich/LongLive-2.0-5B-Diffusers/tree/37664a64cfc38cdc5fabe88576961ef10646e4f1
KindOtherBase modelEfficient-Large-Model/LongLive-2.0-5BVersionRevision 37664a6Publisher@RabinovichCgrade

Model source

Kind
Other
File size
1.34–9.31 GB
Base model
Efficient-Large-Model/LongLive-2.0-5B
Version
vRevision 37664a6
Updated
Oct 31, 2026
Publisher
@Rabinovich
Downloads
18.4K
Parameters
5B
Source
Hugging Face

Source description

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

Requirements

Models

1

Sources

1 source
Hugging FacePrimaryVersion 37664a64cfc38cdc5fabe88576961ef10646e4f1
huggingface.co/Rabinovich/LongLive-2.0-5B-Diffusers/tree/37664a64cfc38cdc5fabe88576961ef10646e4f1

Verified Oct 31

Download files

text_encoder · 3 weight files

All files listed in the provider index are present.

Repository files

File inventory only; completeness is unverified.

Model artifacts

5 artifacts

text_encoder/model-00001-of-00003.safetensors

safetensors · 4.60 GB · SHA-256 a8e861969c74…8f58 · Hugging Face

Download shard

text_encoder/model-00002-of-00003.safetensors

safetensors · 4.64 GB · SHA-256 d57d948ece48…02d7 · Hugging Face

Download shard

text_encoder/model-00003-of-00003.safetensors

safetensors · 1.34 GB · SHA-256 0da9ee284e21…7c5f · Hugging Face

Download shard

transformer/diffusion_pytorch_model.safetensors

safetensors · BF16 (unverified) · 9.31 GB · SHA-256 17c1c2fc0cc8…a293 · Hugging Face

Download file

vae/diffusion_pytorch_model.safetensors

safetensors · FP32 (unverified) · 2.63 GB · SHA-256 62cd18f19438…6f4b · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeJul 11huggingface.co/Rabinovich/LongLive-2.0-5B-Diffusers

--- 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](https://huggingface.co/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) ```bash 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](https://github.com/NVlabs/LongLive). License: [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/)

NoteOct 31huggingface.co/Rabinovich/LongLive-2.0-5B-Diffusers

Source context: 18391 downloads · 0 likes · Pipeline text-to-video · Library diffusers · Repo Rabinovich/LongLive-2.0-5B-Diffusers

NoteAug 16huggingface.co/Rabinovich/LongLive-2.0-5B-Diffusers

Source context: 9508 downloads · 0 likes · Pipeline text-to-video · Library diffusers · Repo Rabinovich/LongLive-2.0-5B-Diffusers