Welcome to Gigantic Work
Learn about the latest Generative AI and Open Source developments
F5-TTS
Advanced text-to-speech synthesis which transform text into natural, expressive speech in your voice
F5-TTS and E2-TTS are text-to-speech (TTS) systems leveraging advanced AI architectures for natural speech synthesis. While both share similarities, F5-TTS is an improved variant of E2-TTS, addressing its limitations.
Stable Diffusion XL (SDXL 1.0)
Create realistic images and art from a description in natural language
Stable Diffusion XL is a text-to-image diffusion model that can also be applied to inpainting, outpainting, and image-to-image translations guided by a text prompt. NSFW filter is enabled which makes it suitable for educational purposes.
OpenAI Whisper
Transcribe video or audio file into subtitles
Whisper is an automatic speech recognition (ASR) system which facilitates transcription in multiple languages and translation into English.
