Over the past several updates, I’ve been working through community reports and taking a closer look at how TT...
Launcher updates
Castwright v1.14.0 — Chinese and Japanese join the cast, and the app grows up on tablets
Quick recap for anyone new: Castwright turns a book into a full-cast audiobook — every character in its own v...
ComfyUI Installer v1.2 — Multiple Instances, GPU Selection and Improved Restarts
🚀 ComfyUI Installer v1.2 — Multiple Instances, GPU Selection and Improved Restarts The Inteliweb AI ComfyUI ...
Remix mode: drop your trained face into ANY scene - 100% on your Mac
Phosphene's new Remix mode fuses two things into a single local render: 1) a Character you trained - a LoRA o...
Songgeneration - Fixed
You may have noticed that all Pinokio installer of SongGeneration-Studio and SongGeneration stopped working. ...
Store
#ai186#tts55#image-generation44#video-generation37#utility34#126#agent24#faceswap21#video21#3d19#music19#audio18#image-edit18#audio-generation15#ui15#voice13#voice-clone13#3dgen12#llm12#agents11#image11#ses-klonlama11#song-generation11#training11#music-generation10#song10#automation9#fubar9#models9#pinokio9
Qwen-Image text to image lora trainer
Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts
OpenKombai: A free, privacy-first alternative to Kombai. Instantly convert screenshots and designs into production-ready React + Tailwind code using local LLMs (Llama 3.2 Vision & Qwen 2.5). No API keys, zero cloud costs.
Contribute to beeble-ai/SwitchLight-Studio development by creating an account on GitHub.
[ICLR 2025] CatVTON is a simple and efficient virtual try-on diffusion model with 1) Lightweight Network (899.06M parameters totally), 2) Parameter-Efficient Training (49.57M parameters trainable) and 3) Simplified Inference (< 8G VRAM for 1024X768 resolution).
Contribute to iamdinhthuan/viterbox-tts development by creating an account on GitHub.
Clone a voice in 5 seconds to generate arbitrary speech in real-time
Python framework designed for algorithmic trading on the MetaTrader 5 platform. This repository provides tools and scripts to automate trading strategies, manage positions, and analyze historical data. It empowers traders to implement and backtest various strategies, enhancing their ability to navigate dynamic market conditions.
Multi-Identity Consistency for Image Customization via Matching Reward https://github.com/bytedance/UMO
Run Wan2GP on Google Colab
Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.
Contribute to presenton/presenton-python-sdk development by creating an account on GitHub.
An app for creating audio-based content such as song covers and speech using Retrieval-based Voice Conversion.
An advanced crypto trading bot written in Python
Contribute to huangzirong566/imastudio development by creating an account on GitHub.
This repo helps you understand how safetensors are structured to store different layers of an LLM and re-shard/re-chunk safetensors files even if they don't fit in the GPU.. ( No Autoclass )
AI-powered speech denoising + enhancement (Gradio web demo + CLI).
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.
EbSynth in Python, version 2