Picture for Hila Chefer

Hila Chefer

Lumiere: A Space-Time Diffusion Model for Video Generation

Add code
Feb 05, 2024
Viaarxiv icon

The Hidden Language of Diffusion Models

Add code
Jun 06, 2023
Figure 1 for The Hidden Language of Diffusion Models
Figure 2 for The Hidden Language of Diffusion Models
Figure 3 for The Hidden Language of Diffusion Models
Figure 4 for The Hidden Language of Diffusion Models
Viaarxiv icon

Discriminative Class Tokens for Text-to-Image Diffusion Models

Add code
Mar 30, 2023
Figure 1 for Discriminative Class Tokens for Text-to-Image Diffusion Models
Figure 2 for Discriminative Class Tokens for Text-to-Image Diffusion Models
Figure 3 for Discriminative Class Tokens for Text-to-Image Diffusion Models
Figure 4 for Discriminative Class Tokens for Text-to-Image Diffusion Models
Viaarxiv icon

Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models

Add code
Jan 31, 2023
Figure 1 for Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models
Figure 2 for Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models
Figure 3 for Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models
Figure 4 for Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models
Viaarxiv icon

Optimizing Relevance Maps of Vision Transformers Improves Robustness

Add code
Jun 02, 2022
Figure 1 for Optimizing Relevance Maps of Vision Transformers Improves Robustness
Figure 2 for Optimizing Relevance Maps of Vision Transformers Improves Robustness
Figure 3 for Optimizing Relevance Maps of Vision Transformers Improves Robustness
Figure 4 for Optimizing Relevance Maps of Vision Transformers Improves Robustness
Viaarxiv icon

No Token Left Behind: Explainability-Aided Image Classification and Generation

Add code
Apr 11, 2022
Figure 1 for No Token Left Behind: Explainability-Aided Image Classification and Generation
Figure 2 for No Token Left Behind: Explainability-Aided Image Classification and Generation
Figure 3 for No Token Left Behind: Explainability-Aided Image Classification and Generation
Figure 4 for No Token Left Behind: Explainability-Aided Image Classification and Generation
Viaarxiv icon

Image-Based CLIP-Guided Essence Transfer

Add code
Oct 26, 2021
Figure 1 for Image-Based CLIP-Guided Essence Transfer
Figure 2 for Image-Based CLIP-Guided Essence Transfer
Figure 3 for Image-Based CLIP-Guided Essence Transfer
Viaarxiv icon

Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers

Add code
Mar 29, 2021
Figure 1 for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers
Figure 2 for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers
Figure 3 for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers
Figure 4 for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers
Viaarxiv icon

Transformer Interpretability Beyond Attention Visualization

Add code
Dec 17, 2020
Figure 1 for Transformer Interpretability Beyond Attention Visualization
Figure 2 for Transformer Interpretability Beyond Attention Visualization
Figure 3 for Transformer Interpretability Beyond Attention Visualization
Figure 4 for Transformer Interpretability Beyond Attention Visualization
Viaarxiv icon