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...
--- 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/)
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…
