Lists (32)
360
42 repositories
3D
100 repositories
Agentic
11 repositories
audio
58 repositories
auth
user management, logins, authorization4 repositories
avatar
22 repositories
comfy
12 repositories
containers
1 repository
design
theming, ui, ux5 repositories
Dev AI Tools
250 repositories
graphs
37 repositories
human
30 repositories
image
2 repositories
Image Extrapolation
32 repositories
LLM
128 repositories
multimodal
79 repositories
music
10 repositories
neural
150 repositories
node editors
14 repositories
Point cloud
10 repositories
SD
27 repositories
Search
15 repositories
shaders
13 repositories
text
52 repositories
Text and story
21 repositories
tools
171 repositories
training
42 repositories
Unreal
7 repositories
User
12 repositories
video
95 repositories
WebXR
27 repositories
wheels
5 repositories
Starred repositories
41
results
for forked starred repositories
Clear filter
haoheliu / all-in-one
Forked from mir-aidj/all-in-oneAll-In-One Music Structure Analyzer
rmusser01 / tldw_server
Forked from the-crypt-keeper/tldwtl/dw (Too Long, Didn't Watch): Your Personal Research Multi-Tool - a naive attempt at 'A Young Lady's Illustrated Primer' (Open Source NotebookLM)
siraxe / LTX-Wizard-GUI
Forked from Lightricks/LTX-Video-TrainerCommunity trainer for Lightricks' LTX Video model 🎬 ⚡️
Hillobar / FramePack-director
Forked from lllyasviel/FramePackAdds quick previewing to test generate segments quickly before rendering,
livepeer / comfystream
Forked from yondonfu/comfystreamA ComfyUI custom node for running real-time media workflows directly within ComfyUI, enabling seamless AI-powered video and audio processing.
Fast and memory-efficient exact attention
Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.
A pipeline parallel training script for diffusion models.
Support for miscellaneous image models. Currently supports: DiT, PixArt, T5 and a few custom VAEs
📄 A curated list of awesome global_rules.md and .windsurfrules files
Neo4j graph construction from unstructured data using LLMs
stackblitz-labs / bolt.diy
Forked from stackblitz/bolt.newPrompt, run, edit, and deploy full-stack web applications using any LLM you want!
kingbri1 / flash-attention
Forked from Dao-AILab/flash-attentionFast and memory-efficient exact attention
peanutcocktail / MindSearch
Forked from InternLM/MindSearcha LLM-based Multi-agent Framework of Web Search Engine similar to Perplexity.ai Pro and SearchGPT
Generative models for conditional audio generation
A suite of Griptape nodes for ComfyUI
kijai / ComfyUI-Diffusers-X-Adapter
Forked from showlab/X-AdapterComfyUI diffusers wrapper node X-Adapter testing
crlandsc / BS-RoFormer
Forked from lucidrains/BS-RoFormerImplementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labs
ykk648 / AnimateDiff-I2V
Forked from guoyww/AnimateDiffAnimateDiff I2V version.
animatediff prompt travel
Depth map library for use with the Control Net extension for Automatic1111/stable-diffusion-webui
Autocomplete your obsidian notes with AI, including Oobabooga text generation webui, through a copilot-like interface.
Ikaros-521 / AI-Vtuber
Forked from sandboxdream/AI-VtuberAI Vtuber是一个由 【ChatterBot/ChatGPT/claude/langchain/chatglm/text-gen-webui/闻达/千问/kimi/ollama】 驱动的虚拟主播【Live2D/UE/xuniren】，可以在 【Bilibili/抖音/快手/微信视频号/拼多多/斗鱼/YouTube/twitch/TikTok】 直播中与观众实时互动 或 直接在本地进行聊…
RandomFractals / svg-path-editor
Forked from Yqnn/svg-path-editorOnline editor to create and manipulate SVG paths
archenovalis / oobabooga-jsonformer-plugin
Forked from hallucinate-games/oobabooga-jsonformer-pluginThis plugin forces models to output JSON of a specified schema using JSONFormer
Convert an equirectangular panorama to six cube faces
oobabooga / GPTQ-for-LLaMa
Forked from qwopqwop200/GPTQ-for-LLaMa4 bits quantization of LLaMa using GPTQ
a2569875 / stable-diffusion-webui-composable-lora
Forked from opparco/stable-diffusion-webui-composable-loraThis extension replaces the built-in LoRA forward procedure.
ntc-ai / conceptmod
Forked from rohitgandikota/erasingModify Concepts from Diffusion Models using a dsl
Experiment in Ultimate SD Upscale focusing on prints, batching, & eliminating options