Creative Models

UniRig AI automates the creation of skeletons and skinning weights for diverse 3D animation assets.

Google Lyria 2 generates music at 48kHz in stereo format based on textual prompts.

ACE-STEP is a diffusion-based foundation model for generating music from text prompts and structured lyrics, optimizing for speed, coherence, and controllability.

Hunyuan3D-2 by PrunaAI generates 3D mesh models from input images using optimized inference parameters.

Generate MagicaVoxel VOX and GLB models from text with Text-to-Voxel. Review detail levels, octree resolution, background removal, inputs and examples.

MusicGen LoRA generates new music tracks based on text prompts and audio inputs, with options for continuation or melody mimicry.