Translated🚀 AI Fully Automated Short Video Engine
- aigc
- comfyui
- image-generation
- tts
72,862 visible repositories in the index
1–24 of 57 · Most stars
Translated🚀 AI Fully Automated Short Video Engine
Image-to-Image Translation in PyTorch
Command-line program to download image galleries and collections from several image hosting sites
pix2tex: Using a ViT to convert images of equations into LaTeX code.
pix2code: Generating Code from a Graphical User Interface Screenshot
https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
abusing github commit history for the lulz
Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.
Synthesizing and manipulating 2048x1024 images with conditional GANs
The repository host gives no description.
Restore videos with pixelated/mosaic regions
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
Agent Skill for generating 2D sprite sheets and map, transparent PNG frames, and animated GIFs from prompts.
SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.
TranslatedOpen-source pan-Latin and pan-CJK (Chinese, Japanese, Korean) pixel font, in a sans-serif style
Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
[ECCV 2024] codes of DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior
Generate clean 2D game sprites & animation atlases — component-row pipeline: state rows, alpha cleanup, frame extraction, runtime atlases. Codex/Claude skill.
Interactive Image Generation via Generative Adversarial Networks
Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.
开源的泛拉丁与泛中日韩像素字体,黑体风格
Entropy Based Sampling and Parallel CoT Decoding
Stealth browser automation for AI agents over MCP and the Chrome DevTools Protocol: navigation, network hooks, DOM extraction, and pixel-accurate UI cloning.