HPC-AI TechnologyVideo model
Open-Sora 2.0
Clip lengthn/a
n/alongest single cliphigher is better
Summary
Open-Sora 2.0 is a video model from HPC-AI Technology. One 11B model supports text-to-video and image-to-video; the project says it is optimized for I2V.
Head-to-head comparisons
vs.Open-Sora 2.0 vs. FLUX.3 VideoNot enough data for a result.Open-Sora 2.0FLUX.3 VideoImage to videon/a1,449Text to videon/a1,4935 s clipn/a$0.85vs.Open-Sora 2.0 vs. Dreamina Seedance 2.5 720pNot enough data for a result.Open-Sora 2.0Dreamina Seedance 2.5 720pImage to videon/a1,477Text to videon/a1,4745 s clipn/an/avs.Open-Sora 2.0 vs. Dreamina Seedance 2.0 720pNot enough data for a result.Open-Sora 2.0Dreamina Seedance 2.0 720pImage to videon/a1,475Text to videon/a1,4795 s clipn/a$0.76vs.Open-Sora 2.0 vs. MiniMax H3Not enough data for a result.Open-Sora 2.0MiniMax H3Image to videon/a1,495Text to videon/a1,4605 s clipn/a$0.65vs.Open-Sora 2.0 vs. Veo 3.1Not enough data for a result.Open-Sora 2.0Veo 3.1Image to videon/a1,398Text to videon/a1,3645 s clipn/a$2.00vs.Open-Sora 2.0 vs. Veo 3.1 FastNot enough data for a result.Open-Sora 2.0Veo 3.1 FastImage to videon/a1,385Text to videon/a1,3625 s clipn/a$0.50
Show all comparisons (94)
All specifications
Architecture
Input and output
Licence and access
Further details
- Input modes
- One 11B model supports text-to-video and image-to-video; the project says it is optimized for I2V.
- Source: Input modes
- Documented resolutions
- The official project lists 256 px and 768 px resolutions.
- Source: Documented resolutions
- Weights and license
- The checkpoint is publicly downloadable; the model card lists Apache 2.0.
- Source: Weights and license
Sources and data date
| Type | Evidence and data date |
|---|---|
| Additional source | HPC-AI Technology (retrieved November 1, 2026) |
| Additional source | HPC-AI Technology (retrieved November 1, 2026) · HPC-AI Technology · Editorial description reviewed November 1, 2026 |