Followed6mo ago
StreamDiffusionV2
github.com/chenfengxu714

StreamDiffusion, Live Stream APP

Discovered6mo ago
ai-toolkit
github.com/peanutcocktail

Various AI scripts. Mostly Stable Diffusion stuff.

Discovered6mo ago
chaplin
github.com/amanvirparhar

A real-time silent speech recognition tool.

Followed6mo ago
ViMax
github.com/HKUDS

"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"

Followed6mo ago
echomimic_v2
github.com/antgroup

[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation

Followed6mo ago
ReactiveGWM
github.com/INV-WZQ

[Arxiv 2026] ReactiveGWM: Steering NPC in Reactive Game World Models

Discovered6mo ago
video2robot
github.com/AIM-Intelligence

End-to-end pipeline converting generative videos (Veo, Sora) to humanoid robot motions

Followed6mo ago
CoMe
github.com/co-me-tokens

[CVPR 26] Release repo of our work "Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers"

Discovered6mo ago
Fooocus-MRE
github.com/MoonRide303

Focus on prompting and generating

Followed6mo ago
NeuralCompanion
github.com/Rakile

Contribute to Rakile/NeuralCompanion development by creating an account on GitHub.

Followed6mo ago
FrankenMotion-Code
github.com/Coral79

[CVPR 2026] FrankenMotion: Part-level Human Motion Generation and Composition

Discovered6mo ago
mlx-whisper-webui
github.com/dadleo

MLX Whisper WebUI fork with added UI controls (Language/Task/Prompt) to prevent hallucinations.

Discovered6mo ago
gpt-2
github.com/nshepperd

Code for the paper "Language Models are Unsupervised Multitask Learners"

Discovered6mo ago
gpt-2
github.com/openai

Code for the paper "Language Models are Unsupervised Multitask Learners"

Discovered6mo ago
openai-community/gpt2 · Hugging Face
huggingface.co/openai-community

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Discovered6mo ago
whichllm
github.com/Andyyyy64

Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.