I presented our paper VETIM at #BMVC2023 three weeks ago!
🔍 It is possible to learn a single token representing a concept in Stable Diffusion using supervision only at the CLIP output and without mimicking visual features from sample images.
Check it out: https://ivrl.github.io/vetim/
🔍 It is possible to learn a single token representing a concept in Stable Diffusion using supervision only at the CLIP output and without mimicking visual features from sample images.
Check it out: https://ivrl.github.io/vetim/
VETIM
Expanding the Vocabulary of Text-to-Image Models only with Text
ivrl.github.io
November 17, 2024 at 9:42 PM
I presented our paper VETIM at #BMVC2023 three weeks ago!
🔍 It is possible to learn a single token representing a concept in Stable Diffusion using supervision only at the CLIP output and without mimicking visual features from sample images.
Check it out: https://ivrl.github.io/vetim/
🔍 It is possible to learn a single token representing a concept in Stable Diffusion using supervision only at the CLIP output and without mimicking visual features from sample images.
Check it out: https://ivrl.github.io/vetim/