We present VisionReward, a general strategy to aligning visual generation models——both image and video generation——with human preferences through a fine-grainedand multi-dimensional framework. We decompose human preferences in images and videos into multiple dimensions,each represented by a series of judgment questions, linearly weighted and summed to an interpretable and accuratescore. To address the challenges of video quality assess-ment, we systematically analyze various dynamic features of videos, which helps VisionReward surpass VideoScore by 17.2% and achieve top performance for video preference prediction.
Here, we present the model of VisionReward-Video.
Using this model
You can quickly install the Python package dependencies and run model inference in our
github
.
Runs of zai-org VisionReward-Video on huggingface.co
443
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
-353
30-day runs
More Information About VisionReward-Video huggingface.co Model
VisionReward-Video huggingface.co is an AI model on huggingface.co that provides VisionReward-Video's model effect (), which can be used instantly with this zai-org VisionReward-Video model. huggingface.co supports a free trial of the VisionReward-Video model, and also provides paid use of the VisionReward-Video. Support call VisionReward-Video model through api, including Node.js, Python, http.
VisionReward-Video huggingface.co is an online trial and call api platform, which integrates VisionReward-Video's modeling effects, including api services, and provides a free online trial of VisionReward-Video, you can try VisionReward-Video online for free by clicking the link below.
zai-org VisionReward-Video online free url in huggingface.co:
VisionReward-Video is an open source model from GitHub that offers a free installation service, and any user can find VisionReward-Video on GitHub to install. At the same time, huggingface.co provides the effect of VisionReward-Video install, users can directly use VisionReward-Video installed effect in huggingface.co for debugging and trial. It also supports api for free installation.