cocktailpeanut

An AI powered mirror

LLM-Based Pseudo Music Captioning

Temporally consistent video editing. A local version of https://huggingface.co/spaces/weizmannscience/tokenflow

LLM Web UI and API

Dense Text-to-Image Generation with Attention Modulation

An open source implementation of Microsoft's VALL-E X zero-shot TTS model

Turn any video into Openpose video https://huggingface.co/spaces/fffiloni/video2openpose2

Windows-focused Hugging Face cache symlink repro harness for testing exact and forced-race scenarios.

Simple script examples that highlight all the Pinokio APIs

llama.cpp with BakLLaVA model describes what does it see (https://github.com/Fuzzy-Search/realtime-bakllava)

moondream1 is a tiny (1.6B parameter) vision language model trained by @vikhyatk that performs on par with models twice its size. It is trained on the LLaVa training dataset, and initialized with SigLIP as the vision tower and Phi-1.5 as the text encoder. https://huggingface.co/spaces/vikhyatk/moondream1

Cross-platform shell.run tests for [[ ]] multiline argument passing.

[NVIDIA GPU ONLY] One click installer for Intel's ldm3d