DepictQA (with vision abstractor to reduce vision token numbers) model weights trained on DQ495K, KonIQ, and SPAQ datasets.
See https://github.com/XPixelGroup/DepictQA for details.
- Downloads last month
- 5
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.