Merge pull request #81 from DawidPludowski/master

add 24-12-02 presentation
MI2DataLab · Dec 15, 2024 · 16b4aaa · 16b4aaa
2 parents 552f1c9 + 05d1631
commit 16b4aaa
Show file tree

Hide file tree

Showing 3 changed files with 8 additions and 1 deletion.
diff --git a/2024/2024_12_02_Null_text_optimization_for_editing_real_images/README.md b/2024/2024_12_02_Null_text_optimization_for_editing_real_images/README.md
@@ -0,0 +1,7 @@
+# NULL-Text Inversion for Editing Real Images Using Guided Diffusion Models
+
+## Abstract
+
+During this seminar, we will talk about image editing using text-guided diffusion models. The important step of this process is to invert the image which can be done in multiple ways. I will present one of the most promising ones - NULL-Text Inversion - presented on CVPR 2023. The authors break the process into two parts: pivotal inversion and NULL-text optimization. The latter uses the well-known DDIM method as the anchor for optimization. I will explain both steps, their advantages over other methods and the use case for these techniques. Additionally, we will see how elements of the prompt are connected to the parts of the image.
+
+The presentation will be based on this paper: [Null-text optimization](https://openaccess.thecvf.com/content/CVPR2023/html/Mokady_NULL-Text_Inversion_for_Editing_Real_Images_Using_Guided_Diffusion_Models_CVPR_2023_paper.html).
diff --git a/2024/2024_12_02_Null_text_optimization_for_editing_real_images/null_text_optimization.pdf b/2024/2024_12_02_Null_text_optimization_for_editing_real_images/null_text_optimization.pdf
diff --git a/README.md b/README.md
@@ -17,7 +17,7 @@ Join us at https://meet.drwhy.ai.
 * 04.11 - [Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2024/2024_11_04_Unlocking_the_Power_of_Spatial_and_Temporal_Information_in_Medical_Multimodal_Pre-training) - Bartosz Kochański
 * 18.11 - User study: Visual Counterfactual Explanations for Improved Model Understanding - Bartek Sobieski
 * 25.11 - [Vision Transformers provably learn spatial structure](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2024/2024_11_25_Vision_Transformers_provably_learn_spatial_structure) - Vladimir Zaigrajew
-* 02.12 - Null-text Inversion for Editing Real Images using Guided Diffusion Models - Dawid Płudowski
+* 02.12 - [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://github.com/MI2DataLab/MI2DataLab_Seminarium/tree/master/2024/2024_12_02_Null_text_optimization_for_editing_real_images) - Dawid Płudowski
 * 09.12 - Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training - Tymoteusz Kwieciński
 * 20.01 - Connecting counterfactual and attributions modes of explanation - Jan Jakubik