Store

Declaratively define and modify agents and multi-agent workflows through a point and click, drag and drop interface (e.g., you can select the parameters of two agents that will communicate to solve your task).

Upload a clean 20 seconds WAV file of the vocal persona you want to mimic, type your text-to-speech prompt and hit submit! A local version of https://huggingface.co/spaces/fffiloni/instant-TTS-Bark-cloning

enhance the resolution and spatiotemporal continuity of text-generated videos and image-generated videos

LLM Web UI and API

A Real-Time Text-to-Image Generation Model

an open vision-language model by Google. PaliGemma is designed as a versatile model for transfer to a wide range of vision-language tasks such as image and short video caption, visual question answering, text reading, object detection and object segmentation https://huggingface.co/spaces/google/paligemma

Brought to you by Cohee, RossAscends, and the SillyTavern community, SillyTavern is a local-install interface that allows you to interact with text generation AIs (LLMs) to chat and roleplay with custom characters.

Generative AI for Professional Creatives

Customized ID Consistent for human: https://github.com/JackAILab/ConsistentID

Rerender_A_Video: Zero-Shot Text-Guided Video-to-Video Translation

A Gradio UI for XTTSv2 and RVC, allowing for real-time voice conversion.

SuperPrompter is a Python-based application that utilises the SuperPrompt-v1 model to generate optimised text prompts for AI/LLM image generation (for use with Stable Diffusion etc...) from user prompts.

The script utilizes various deep learning models to create detailed character cards, including names, summaries, personalities, greeting messages, and character avatars.

Next generation face swapper and enhancer

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

Stable Diffusion UI with patches by lllyasviel

Flexible Automapper for Beatsaber made for any difficulty

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

Massively Multilingual Speech (MMS): Persian Text-to-Speech