Task
Image Classification
C
cafeai/cafe_aesthetic
Image Classification·cafeai· 3.5K· 56
Since people are downloading this and I don't know why, I'll add some information. This model is an image classifier fine-tuned on microsoft/beit-base-patch16-384. Its purpose is to be used in the dataset conditioning step for the Waifu Diffusion project, a fine-tune effort for Stable Diffusion. As WD1.4 is planned to have a significantly large dataset (~15m images), it is infeasible to analyze ev
# pull & run locally
pip install mlforge-sdk && mlforge pull cafeai/cafe_aesthetic
pip install mlforge-sdk && mlforge pull cafeai/cafe_aesthetic
Model details
Provider
cafeai
Framework
transformers
Size
717 MB
License
agpl-3.0
Downloads
3.5K
Likes
56
Updated
2022-11-23
About cafeai/cafe_aesthetic
Since people are downloading this and I don't know why, I'll add some information. This model is an image classifier fine-tuned on microsoft/beit-base-patch16-384. Its purpose is to be used in the dataset conditioning step for the Waifu Diffusion project, a fine-tune effort for Stable Diffusion. As WD1.4 is planned to have a significantly large dataset (~15m images), it is infeasible to analyze every image manually to determine whether or not it should be included in the final training dataset. This image classifier is trained on approximately 3.5k real-life and anime/manga images. Its purpose is to remove aesthetically worthless images from our dataset by classifying them as "notaesthetic". The image classifier was trained to err on the side of caution and will generally tend to include images unless they are in a "manga-like" format, have messy lines and/or are sketches, or include an unacceptable amount of text (namely text that covers the primary subject of the image). The idea is that certain images will hurt a SD fine-tune.