Large Language Model (LLM) Playground
Multimodal Playground
RAG @ Large Language Model (LLM) Playground
Multimodal RAG Agent
An end-to-end (e2e) Voice Language Model by Fish Audio.
Generate text from audio recordings
Upgraded to v1.0!
Build and deploy custom workflows for language tasks
Generate a video from an image, audio, and pose data
Extract garment images from everyday images!
Identity-Preserving Text-to-Video Generation
Generate relit images from your photo
Image generator/identifier/reposer