# Multi-shot Video Generation on 100 hierarchical prompts with transitions

Source: [Multi-shot Video Generation on 100 hierarchical prompts with transitions](<https://www.sota2.com/research/sota/multi-shot-video-generation-on-100-hierarchical-prompts-with-transitions>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-04T08:04:02.420Z

Evaluation of multi-shot video generation models using the '100 hierarchical prompts with transitions' dataset, focusing on transition control, inter-shot/intra-shot consistency, and aesthetic quality.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Multi-shot Video Generation |
| Dataset (including any stated split) | 100 hierarchical prompts with transitions |
| Metric | Inter-shot Semantic Consistency Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Inter-shot Semantic Consistency Score](<https://www.sota2.com/research/sota/multi-shot-video-generation-on-100-hierarchical-prompts-with-transitions.md?metric=Inter-shot%20Semantic%20Consistency%20Score>): Higher is better; unit: PERCENT.

- [Transition Control Score](<https://www.sota2.com/research/sota/multi-shot-video-generation-on-100-hierarchical-prompts-with-transitions.md?metric=Transition%20Control%20Score>): Higher is better; unit: PERCENT.

- [Inter-shot Semantic Gap](<https://www.sota2.com/research/sota/multi-shot-video-generation-on-100-hierarchical-prompts-with-transitions.md?metric=Inter-shot%20Semantic%20Gap>): Lower is better; unit: SCALAR.

- [Inter-shot Visual Consistency Score](<https://www.sota2.com/research/sota/multi-shot-video-generation-on-100-hierarchical-prompts-with-transitions.md?metric=Inter-shot%20Visual%20Consistency%20Score>): Higher is better; unit: PERCENT.

- [Inter-shot Visual Gap](<https://www.sota2.com/research/sota/multi-shot-video-generation-on-100-hierarchical-prompts-with-transitions.md?metric=Inter-shot%20Visual%20Gap>): Lower is better; unit: SCALAR.

- [Intra-shot Subject Consistency](<https://www.sota2.com/research/sota/multi-shot-video-generation-on-100-hierarchical-prompts-with-transitions.md?metric=Intra-shot%20Subject%20Consistency>): Higher is better; unit: PERCENT.

- [Intra-shot Background Consistency](<https://www.sota2.com/research/sota/multi-shot-video-generation-on-100-hierarchical-prompts-with-transitions.md?metric=Intra-shot%20Background%20Consistency>): Higher is better; unit: PERCENT.

- [Aesthetic Quality](<https://www.sota2.com/research/sota/multi-shot-video-generation-on-100-hierarchical-prompts-with-transitions.md?metric=Aesthetic%20Quality>): Higher is better; unit: PERCENT.

- [Semantic Consistency](<https://www.sota2.com/research/sota/multi-shot-video-generation-on-100-hierarchical-prompts-with-transitions.md?metric=Semantic%20Consistency>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Inter-shot Semantic Consistency Score | Result date | Report paper |
| --- | --- | --- | --- |
| CineTrans-Unet | 80.95 | Not recorded | 68fa7ab41e209131cea84b40 |
| CineTrans-DiT | 78.58 | Not recorded | 68fa7ab41e209131cea84b40 |
| Wanx2.1-T2V-turbo | 64.31 | Not recorded | 68fa7ab41e209131cea84b40 |
| HunyuanVideo | 57.23 | Not recorded | 68fa7ab41e209131cea84b40 |
| HunyuanVideo + Cinematron | 56.31 | Not recorded | 68fa7ab41e209131cea84b40 |
| StoryDiffusion + CogVideoXI2V | 52.14 | Not recorded | 68fa7ab41e209131cea84b40 |
| CogVideoX | 51.5 | Not recorded | 68fa7ab41e209131cea84b40 |

### CineTrans-Unet

Inter-shot Semantic Consistency Score: 80.95. Result ID: 69a7e6066dbb7075b94c934c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ab41e209131cea84b40.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ab41e209131cea84b40.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CineTrans-DiT

Inter-shot Semantic Consistency Score: 78.58. Result ID: 69a7e6066dbb7075b94c934d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ab41e209131cea84b40.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ab41e209131cea84b40.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Wanx2.1-T2V-turbo

Inter-shot Semantic Consistency Score: 64.31. Result ID: 69a7e6066dbb7075b94c934a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ab41e209131cea84b40.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76f7d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### HunyuanVideo

Inter-shot Semantic Consistency Score: 57.23. Result ID: 69a7e6066dbb7075b94c9349.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ab41e209131cea84b40.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77581e209131cea72919.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### HunyuanVideo + Cinematron

Inter-shot Semantic Consistency Score: 56.31. Result ID: 69a7e6066dbb7075b94c9348.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ab41e209131cea84b40.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### StoryDiffusion + CogVideoXI2V

Inter-shot Semantic Consistency Score: 52.14. Result ID: 69a7e6066dbb7075b94c9347.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ab41e209131cea84b40.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CogVideoX

Inter-shot Semantic Consistency Score: 51.5. Result ID: 69a7e6066dbb7075b94c934b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ab41e209131cea84b40.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a01e209131cea74741.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
