---
title: "Open-Sora-Plan"
description: "PKU Yuan Group Open-Sora-Plan v1.3 T2V. Studio demo passed at 640×352 / 93 frames / 18 fps / 100 Euler-ancestral steps; runner parity is still unrecorded."
modelId: "open-sora-plan"
pageSource: authored
---
Open-Sora-Plan is Peking University Yuan Group's open text-to-video project — independent of HPC-AI Tech's [Open-Sora](/docs/guides/supported-models/open-sora) despite the similar name. Hugging Face weights ship under **LanguageBind**; GitHub is **PKU-YuanGroup**. This card is the **v1.3.0 GPU** route. WorldFoundry bridges the in-tree official sampler (`OpenSoraPlanPipeline`) and reports missing checkpoints at runtime.
The paper is [Open-Sora Plan: Open-Source Large Video Generation Model](https://arxiv.org/abs/2412.00131). Code: [PKU-YuanGroup/Open-Sora-Plan](https://github.com/PKU-YuanGroup/Open-Sora-Plan). Weights: [LanguageBind/Open-Sora-Plan-v1.3.0](https://huggingface.co/LanguageBind/Open-Sora-Plan-v1.3.0). `paper.png` is the title thumb only.
## What it is for
Prompt-only T2V: required `prompt`, artifact `open-sora-plan.mp4`. There is **no local I2V or V2V** on this card (the paper discusses condition controllers; they are not this binding). Use v1.3.0 for GPU. LanguageBind also published v1.0.0–v1.2.0 and a **v1.5.0** line aimed at Ascend / MindSpeed — that last one is not the validated WorldFoundry GPU path. Compare open T2V quality on [VBench](/docs/evaluation/benchmark-hub/vbench) without treating it as an ingested rank.
## Inference
Studio/API validation replayed the official v1.3 GPU script (`sample_t2v_v1_3.sh` / Tokyo street):
| Knob | Recorded value |
| --- | --- |
| Size | **640×352** (`any93x640x640`; decodes as 93 non-empty 640×352 frames) |
| Frames | **93** |
| FPS | **18** |
| Sampler | **EulerAncestralDiscrete**, `v_prediction`, `--rescale_betas_zero_snr` |
| Steps | **100** |
| Guidance | **7.5** |
| Seed | **1234** |
| Text encoder | `google/mt5-xxl` (`max_sequence_length=512`) |
| VAE | **WF-VAE** `WFVAEModel_D8_4x8x8` under the checkpoint `vae/` subdir |
Visual QA on that prompt is recorded. Catalog runner evidence is still **not recorded**. The wrapper default is `nproc_per_node=1` for a single prompt; the official multi-prompt script uses `torchrun --nproc_per_node=8`. Catalog VRAM is unset.
## Running in WorldFoundry
`worldfoundry-eval run open-sora-plan` in `worldfoundry-unified-cu128` (Python 3.11, CUDA 12.8). Stage `LanguageBind/Open-Sora-Plan-v1.3.0` and `google/mt5-xxl`. `scripts/inference/prepare_model_infer.sh` places the ~50 GB text encoder once so it is not copied into both `WORLDFOUNDRY_CKPT_DIR` and `WORLDFOUNDRY_HFD_ROOT`. License on the recorded v1.3 card is **MIT**. Status: **Runner parity pending**.