rain's starred repositories
AniPortrait
AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
pytorch-fid
Compute FID scores with PyTorch.
Awesome-Federated-Machine-Learning
Everything about federated learning, including research papers, books, codes, tutorials, videos and beyond
conditional-flow-matching
TorchCFM: a Conditional Flow Matching library
FaceFormer
[CVPR 2022] FaceFormer: Speech-Driven 3D Facial Animation with Transformers
RectifiedFlow
Official Implementation of Rectified Flow (ICLR2023 Spotlight)
Anti-DreamBooth
Anti-DreamBooth: Protecting users from personalized text-to-image synthesis (ICCV 2023)
common_metrics_on_video_quality
You can easily calculate FVD, PSNR, SSIM, LPIPS for evaluating the quality of generated or predicted videos.
MMA-Diffusion
[CVPR2024] MMA-Diffusion: MultiModal Attack on Diffusion Models
Awesome-MLLM-Safety
Accepted by IJCAI-24 Survey Track
curiosity_redteam
Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizXgXU)
Awesome-T2I-safety-Papers
List of T2I safety papers, updated daily, welcome to discuss using Discussions
Universal-Prompt-Injection
The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".
JailBreakV_28K
JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and further assess the robustness and safety of MLLMs against a variety of jailbreak attacks.
Multimodal-Roadmap-for-freshman
本项目用于Multimodal领域新手的学习路线,包括该领域的经典论文,项目及课程。旨在希望学习者在一定的时间内达到对这个领域有较为深刻的认知,能够自己进行的独立研究。
Divide-and-Conquer-Attack
Divide-and-Conquer Attack: Harnessing the Power of LLM to Bypass the Censorship of Text-to-Image Generation Mode