Picture for Baldo Faieta

Baldo Faieta

Controlled and Conditional Text to Image Generation with Diffusion Prior

Add code
Feb 23, 2023
Viaarxiv icon

HyperNST: Hyper-Networks for Neural Style Transfer

Add code
Aug 09, 2022
Figure 1 for HyperNST: Hyper-Networks for Neural Style Transfer
Figure 2 for HyperNST: Hyper-Networks for Neural Style Transfer
Figure 3 for HyperNST: Hyper-Networks for Neural Style Transfer
Figure 4 for HyperNST: Hyper-Networks for Neural Style Transfer
Viaarxiv icon

StyleBabel: Artistic Style Tagging and Captioning

Add code
Mar 11, 2022
Figure 1 for StyleBabel: Artistic Style Tagging and Captioning
Figure 2 for StyleBabel: Artistic Style Tagging and Captioning
Figure 3 for StyleBabel: Artistic Style Tagging and Captioning
Figure 4 for StyleBabel: Artistic Style Tagging and Captioning
Viaarxiv icon

Multimodal Contrastive Training for Visual Representation Learning

Add code
Apr 26, 2021
Figure 1 for Multimodal Contrastive Training for Visual Representation Learning
Figure 2 for Multimodal Contrastive Training for Visual Representation Learning
Figure 3 for Multimodal Contrastive Training for Visual Representation Learning
Figure 4 for Multimodal Contrastive Training for Visual Representation Learning
Viaarxiv icon

ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity

Add code
Mar 17, 2021
Figure 1 for ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity
Figure 2 for ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity
Figure 3 for ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity
Figure 4 for ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity
Viaarxiv icon

Multitask Text-to-Visual Embedding with Titles and Clickthrough Data

Add code
May 30, 2019
Figure 1 for Multitask Text-to-Visual Embedding with Titles and Clickthrough Data
Figure 2 for Multitask Text-to-Visual Embedding with Titles and Clickthrough Data
Figure 3 for Multitask Text-to-Visual Embedding with Titles and Clickthrough Data
Figure 4 for Multitask Text-to-Visual Embedding with Titles and Clickthrough Data
Viaarxiv icon