Generate speech in a cloned or custom voice
AI tools for the portfolio photo editor (Kontext, LaMa)
Music Generation Foundation Model v1.5
Whisper large-v3-turbo transcription with timestamps
Text-to-sound effects and music (AudioLDM2, MusicGen)
Krea 2 Turbo text-to-image (8 steps) on ZeroGPU
Z-Image-Turbo text-to-image (8 steps) on ZeroGPU
Text-to-video with Wan2.1-T2V-1.3B on ZeroGPU
Plain-English questions to DuckDB SQL (Qwen2.5-Coder-7B)
SDXL Lightning text-to-image for Feliks's portfolio lab
Neural text-to-speech on Kokoro-82M (ZeroGPU)