Shot Reader 8B vs WeMM-Video-2B
Compare documented capabilities and access. A dash means a comparable figure is unavailable.
| Specification | ||
|---|---|---|
| Task | Shot analysis | Audio-visual understanding |
| Published capabilities | Extracts camera framing, lens, movement and subject positions from footage using a fine-tuned Qwen3-VL model. | Answers questions in Chinese or English about video frames and their soundtrack. Supports direct responses and a thinking mode. |
| Model size | 8B backbone | 2B dense language backbone |
| Access | Downloadable weights | Public BF16 checkpoint and quantized releases |
| Result | Structured JSON shot sheet | Text responses, including descriptions and speech transcripts |
| Sources | Model weights | Model weights · Additional documentation |
| Inputs | Text, Images, Video | Text, Images, Audio, Video |
| Weights | Open weights · Apache-2.0 | Open weights · Apache-2.0 |
| Released | Nov 19, 2026 | Nov 20, 2026 |