arxiv:2407.11814
Vasco Ramos
asiimo
·
AI & ML interests
Multimodal Generation, Factual Consistency
Recent Activity
upvoted
an
article
20 days ago
We’re open-sourcing our text-to-image model and the process behind it
upvoted
an
article
4 months ago
Explaining the SDXL latent space
authored
a paper
9 months ago
Contrastive Sequential-Diffusion Learning: An approach to Multi-Scene
Instructional Video Synthesis
Organizations
