WorldFoundry
English中文

Open-Sora

Method overview: Open-Sora’s video generation stack from the paper.

HPC-AI Tech Open-Sora v1.2 T2V via STDiT-v3. WorldFoundry pins 480p / 51 frames / 24 fps / 30 rectified-flow steps; runner parity is not recorded.

Edit this pageGitHubMarkdown

Open-Sora is HPC-AI Tech's open text-to-video stack. This catalog card is the v1.2 STDiT-v3 inference route — prompt in, open-sora.mp4 out — not Open-Sora-Plan. The WorldFoundry path is an official-CLI bridge under worldfoundry/synthesis/visual_generation/open_sora. It reports missing weights at runtime; it does not download them.

Official paper teaser: Open-Sora video generation samples from the paper.
Official paper teaser: Open-Sora video generation samples from the paper.
Method overview: Open-Sora’s video generation stack from the paper.
Method overview: Open-Sora’s video generation stack from the paper.

The catalog paper field points at Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k. That is a later report. The checkpoints this page actually stages are Open-Sora v1.2: hpcai-tech/OpenSora-STDiT-v3 plus hpcai-tech/OpenSora-VAE-v1.2. Project page: hpcaitech.github.io/Open-Sora. Code: hpcaitech/Open-Sora. paper.png is the title thumb only.

Build your run

Pipeline
OpenSoraPipelineworldfoundry.pipelines.video_official.pipeline_official_video
TaskInteractive Video interactive-video
Environmentworldfoundry-unified-cu121
DeviceCUDA 12.1
Runnerworldfoundry.pipeline
Loadingfrom_pretrained
Invocationnative_or_standard_invocation
worldfoundry-eval run \
  open-sora \
  --pipeline.task-profile interactive-video \
  --json

What it is for

Text-to-video only. OpenSoraPipeline takes a required prompt and writes open-sora.mp4. There is no local I2V or V2V on this card (upstream 1.3 / 2.0 lines advertise those; they are not bound here). Forgetting the video VAE is the usual failure. Compare clip quality on VBench — the suite Open-Sora releases usually cite, not an ingested WorldFoundry table.

Inference

The official-CLI wrapper overrides the vendored sample.py onto the Hugging Face demo quality preset:

KnobWorldFoundry launchVendored sample.py before override
Resolution480p240p
Aspect9:169:16
Frames51 (~2 s)51
FPS / save FPS2424
Samplerrectified flow (rflow, timestep transform on)same
Steps3030
Guidance7.0 (--cfg-scale)7.0
Aesthetic6.5 (--aes); no forced motion score6.5, flow=None
Seed102442

Flash-attn and layernorm kernels are forced off on the recorded command. Catalog VRAM is unset. An older hpcai-tech/OpenSora-STDiT-v1-HQ-16x512x512 repo is listed; it is not the default STDiT-v3 path. An STDiT-v2 candidate returned 401 and is not listed.

Running in WorldFoundry

worldfoundry-eval run open-sora in worldfoundry-unified-cu128 (Python 3.11, CUDA 12.8). Stage three Apache-2.0 public repos before launch:

  • hpcai-tech/OpenSora-STDiT-v3 (config.json + model.safetensors)
  • hpcai-tech/OpenSora-VAE-v1.2 (same pair)
  • DeepFloyd/t5-v1_1-xxl (index + two .bin shards + spiece.model)

Status: Runner parity pending. A successful command is not a checkpoint-backed GPU artifact in this workspace.