Fronk Supakorn's repositories
scedit-pytorch
Implementation of "SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing"
face-alignment-tensorrt
:fire::rocket: 2x runtime improvement with TensorRT
paper_replication
This repository compiles all of my research and study efforts, where I delve into cutting-edge AI/ML/DL research papers to achieve a deeper understanding. Through this process, I aim to enhance both my theoretical comprehension and practical coding skills.
AnyDoor
Official implementations for paper: Anydoor: zero-shot object-level image customization
audio2photoreal
Code and dataset for photorealistic Codec Avatars driven from audio
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
dreamstyler
Official implementation of "DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion Models" (AAAI24)
dreamtalk
Official implementations for paper: DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models
FineControlNet
Official Pytorch Implementation of "FineControlNet: Fine-level Text Control for Image Generation with Spatially Aligned Text Control Injection", 2023
GPAvatar
[ICLR 2024] Generalizable and Precise Head Avatar from Image(s)
i2vgen-xl
Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models
ImageDream
The code releasing for https://image-dream.github.io/
LGM
LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.
MarketSmith-Indicator-TradingView
These scripts are designed to allow everyone using a free TradingView subscription plan to replicate the MarketSmith template. The MarketSmith Indicator is a 4 in 1 indicator which contains the bars display, the SMA/EMA Daily and Weekly, the RS Rating (Rating in the style of IBD) and High Low points.
MirrorDiffusion
zero-shot image-to-image translation, diffusion model, prompt, image-to-image translation
OOTDiffusion
Official implementation of OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on
Open-Sora-Plan
This project aim to reproducing Sora (Open AI T2V model), but we only have limited resource. We deeply wish the all open source community can contribute to this project.
roop-unleashed
Evolved Fork of roop with Web Server and lots of additions
sketch2manga
Apply screentone to line drawings or colored illustrations with diffusion models.
StyleLipSync
[ICCV 2023] Official pytorch implementation of "StyleLipSync: Style-based Personalized Lip-sync Video Generation".
SyncTalk
[CVPR 2024] This is the official source for our paper "SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis"
UDiffText
UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models
VASA-1-hack
Using Claude Opus to reverse engineer code from VASA white paper - WIP - (this is for La Raza 🎷)