ID-ControlNet conditions latent diffusion models on facial identity embeddings and uses consistency losses to improve identity preservation in face inpainting.
NeurIPS , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Face inpainting with Identity Preserving Latent Diffusion Models
ID-ControlNet conditions latent diffusion models on facial identity embeddings and uses consistency losses to improve identity preservation in face inpainting.