Upload README.md
Browse files
README.md
CHANGED
|
@@ -12,12 +12,12 @@ tags:
|
|
| 12 |
The emergence of large-scale multi-modal generative models has drastically advanced artificial intelligence, introducing unprecedented levels of performance and functionality.
|
| 13 |
However, optimizing these models remains challenging due to historically isolated paths of model-centric and data-centric developments, leading to suboptimal outcomes and inefficient resource utilization.
|
| 14 |
In response, we present a novel sandbox suite tailored for integrated data-model co-development. This sandbox provides a comprehensive experimental platform, enabling rapid iteration and insight-driven refinement of both data and models.
|
| 15 |
-
Our proposed "Probe-Analyze-Refine" workflow, validated through applications on [T2V-Turbo](https://github.com/Ji4chenLi/t2v-turbo) and achieve a new
|
| 16 |
|
| 17 |
|
| 18 |
## Model description 🚀
|
| 19 |
|
| 20 |
-
This repository
|
| 21 |
|
| 22 |
|
| 23 |
## Guidelines on Inappropriate and Prohibited Use 🚫
|
|
|
|
| 12 |
The emergence of large-scale multi-modal generative models has drastically advanced artificial intelligence, introducing unprecedented levels of performance and functionality.
|
| 13 |
However, optimizing these models remains challenging due to historically isolated paths of model-centric and data-centric developments, leading to suboptimal outcomes and inefficient resource utilization.
|
| 14 |
In response, we present a novel sandbox suite tailored for integrated data-model co-development. This sandbox provides a comprehensive experimental platform, enabling rapid iteration and insight-driven refinement of both data and models.
|
| 15 |
+
Our proposed "Probe-Analyze-Refine" workflow, validated through applications on [T2V-Turbo](https://github.com/Ji4chenLi/t2v-turbo) and achieve a new state-of-the-art on [VBench leaderboard](https://huggingface.co/spaces/Vchitect/VBench_Leaderboard) with 1.09% improvement from T2V-Turbo. Our experiment code and dataset are released at [Data-Juicer Sandbox](https://github.com/modelscope/data-juicer/blob/main/docs/Sandbox.md).
|
| 16 |
|
| 17 |
|
| 18 |
## Model description 🚀
|
| 19 |
|
| 20 |
+
This repository includes the `unet_lora.pt` file, which can transform [VideoCrafter2](https://ailab-cvc.github.io/videocrafter2/) into our <span style="font-family: 'Courier New', monospace; font-weight: bold">Data-Juicer-T2V</span>. Please refer to the code in [T2V-Turbo](https://github.com/Ji4chenLi/t2v-turbo) to utilize our model effectively.
|
| 21 |
|
| 22 |
|
| 23 |
## Guidelines on Inappropriate and Prohibited Use 🚫
|