Added regional generation papers

julioasotodv · Nov 6, 2024 · 66ccc2c · 66ccc2c
1 parent 8f1298a
commit 66ccc2c
Show file tree

Hide file tree

Showing 5 changed files with 31 additions and 2 deletions.
diff --git a/Slides-handout_version.ipynb b/Slides-handout_version.ipynb
@@ -2429,7 +2429,12 @@
    "id": "19c5aa13-1eb3-479c-b0ae-672fa2c4676d",
    "metadata": {},
    "source": [
-    "\\small General multi-task diffusion models:\n",
+    "\\small Regional generation:\n",
+    "\n",
+    "- [\\color{SkyBlue}{Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs}](https://arxiv.org/abs/2401.11708) by Yang et al. [2024]\n",
+    "- [\\color{SkyBlue}{Training-free Regional Prompting for Diffusion Transformers}](https://arxiv.org/abs/2411.02395) by Chen et al. [2024]]\n",
+    "\n",
+    "General multi-task diffusion models:\n",
     "\n",
     "- [\\color{SkyBlue}{OmniGen: Unified Image Generation}](https://arxiv.org/abs/2409.11340) by Xiao et al. [2024]"
    ]

diff --git a/Slides.ipynb b/Slides.ipynb
@@ -2512,7 +2512,12 @@
    "id": "bd52f057-cdfa-4d4d-b6ca-90a3c1ab9665",
    "metadata": {},
    "source": [
-    "\\small General multi-task diffusion models:\n",
+    "\\small Regional generation:\n",
+    "\n",
+    "- [\\color{SkyBlue}{Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs}](https://arxiv.org/abs/2401.11708) by Yang et al. [2024]\n",
+    "- [\\color{SkyBlue}{Training-free Regional Prompting for Diffusion Transformers}](https://arxiv.org/abs/2411.02395) by Chen et al. [2024]\n",
+    "\n",
+    "General multi-task diffusion models:\n",
     "\n",
     "- [\\color{SkyBlue}{OmniGen: Unified Image Generation}](https://arxiv.org/abs/2409.11340) by Xiao et al. [2024]"
    ]

diff --git a/docs/Slides-handout_version.pdf b/docs/Slides-handout_version.pdf
diff --git a/docs/Slides.pdf b/docs/Slides.pdf
diff --git a/references_slides.bib b/references_slides.bib
@@ -857,6 +857,25 @@ @misc{wang2024rectifieddiffusionstraightnessneed
       url={https://arxiv.org/abs/2410.07303}, 
 }
 
+@inproceedings{
+yang2024mastering,
+title={Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal {LLM}s},
+author={Ling Yang and Zhaochen Yu and Chenlin Meng and Minkai Xu and Stefano Ermon and Bin CUI},
+booktitle={Forty-first International Conference on Machine Learning},
+year={2024},
+url={https://openreview.net/forum?id=DgLFkAPwuZ}
+}
+
+@misc{chen2024trainingfreeregionalpromptingdiffusion,
+      title={Training-free Regional Prompting for Diffusion Transformers}, 
+      author={Anthony Chen and Jianjin Xu and Wenzhao Zheng and Gaole Dai and Yida Wang and Renrui Zhang and Haofan Wang and Shanghang Zhang},
+      year={2024},
+      eprint={2411.02395},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2411.02395}, 
+}
+
 @misc{xiao2024omnigenunifiedimagegeneration,
       title={OmniGen: Unified Image Generation}, 
       author={Shitao Xiao and Yueze Wang and Junjie Zhou and Huaying Yuan and Xingrun Xing and Ruiran Yan and Shuting Wang and Tiejun Huang and Zheng Liu},