Generate lip-synced video from video/image and audio

Make Custom Voices With KokoroTTS

Ghibli Studio LoRA based Text to Image Generation

Create a large, deduplicated dataset for LLM pre-training

Interact with an AI by sending text, images, or audio

VLMEvalKit Eval Results in video understanding benchmark

Launch MTEB Arena to compare models

Run and submit answers to questions

Generate insights from charts using text prompts

Use NVIDIA H100 GPU

Convert and upload Hugging Face models to MLX format

Generate speech from text in multiple languages

Convert text to speech in multiple languages

FaceOnLive On-Premise Solution

Vote on AI responses to rank models

Communicate with a multimodal chatbot

Train a custom video model

Consistency generation of portrait and subject

Create personalized avatars from images