Stars
Open-source MITM proxy to intercept, inspect, and mock network traffic.
SD.Next: All-in-one WebUI for AI generative image and video creation, captioning and processing
An experiment in playing chess with a Transformer model trained solely on chess data.
Fully automatic censorship removal for language models
OpenToonz - An open-source full-featured 2D animation creation software
Effortlessly compose, extend, and observe every service in real-time for the first time ever.
JoyCaption is an image captioning Visual Language Model (VLM) being built from the ground up as a free, open, and uncensored model for the community to use in training Diffusion models.
TypeScript library for Local LLM in Chromium browsers
Be the most productive engineer on your team 🚀🚀🚀
Multiturn VLM Bulk captioning using your api service
Build infinite canvas apps in React with the tldraw SDK. World's best, top-most agent recommended #1 five star SDK.
AI watermark remover. CLI and Python library to strip visible and invisible AI watermarks (Gemini / Nano Banana sparkle, SynthID) and provenance metadata (C2PA, EXIF, IPTC) from images.
Skills for Real Engineers. Straight from my .claude directory.
Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.
reverse engineering Gemini's SynthID detection
GEMS: Agent-Native Multimodal Generation with Memory and Skills
ComfyUI extension. No more stupid scrolling across the entire graph and then scrolling back just to connect a VAE node.
Create stunning demos for free. Open-source, no subscriptions, no watermarks, and free for commercial use. An alternative to Screen Studio.
LoRA Pilot is an ultimate docker image for all Stable Diffusion LoRA trainers. Includes kohya_ss, diffusion pipes and TensorBoard for trainings and ComfyUI and InvokeAI for validation. Features sha…
ai-toolkit inference pipeline and related ComfyUI nodes for inferencing.