Generative media for advanced learners
271 resources · page 7 of 9
Suno Launches Licensed AI Music Models After Warner Copyright Settlement (ProPakistani)
by ProPakistani
ProPakistani report on Suno launching licensed v6 music models built with Warner, BMG and Believe.
@sunomusic (Suno)
by Suno
X account of Suno: updates on its AI music generation app and models.
SadTalker
by OpenTalker
SadTalker GitHub repo (CVPR 2023): generating talking-head video from a single portrait and audio.
Deezer says more than 50% of daily uploads are AI-generated (TechCrunch)
by TechCrunch
TechCrunch report on Deezer saying more than half of daily music uploads are AI-generated.
AudioCraft: MusicGen docs
MusicGen documentation in Meta's AudioCraft GitHub repo: text- and melody-conditioned music generation.
Coqui TTS
by coqui
Coqui TTS GitHub repo: deep learning toolkit for text-to-speech with pretrained voices and a command line.
Tongyi-MAI (Z-Image) HF
by Tongyi-MAI
Tongyi-MAI Hugging Face organisation (Alibaba): Z-Image image generation models.
TRELLIS.2
by Top 3D AI
Top 3D AI listing for Microsoft TRELLIS.2, a 4B-parameter image-to-3D model, with ratings.
TRELLIS (Microsoft)
by Microsoft
Microsoft TRELLIS GitHub repo: structured 3D latents model for 3D asset generation.
Tripo
by Tripo AI
Tripo AI: generator of 3D models from text or images for games, printing and animation.
Tripo AI v3.1
by Top 3D AI
Top 3D AI listing for Tripo AI v3.1 3D generation platform with texturing and rigging, with ratings.
Tripo JavaScript SDK
by VAST
VAST tripo-js-sdk GitHub repo: JavaScript and TypeScript SDK for the Tripo3D v3 API.
TripoSG official implementation
by VAST
VAST TripoSG GitHub repo: 3D shape synthesis model with code and weight links.
Triverse 3.0
by Top 3D AI
Top 3D AI listing for Triverse 3.0 text- and image-to-3D generator with ratings.
Triverse AI
by Triverse AI
Triverse AI: generator producing 3D models with PBR maps from images and text, exporting to game engines.
Udio
by Udio
Udio: AI music generator; settled UMG's copyright suit in October 2025 and announced a licensed platform.
Suno's Legal Battle Against Sony Music and UMG (Digital Music News)
Digital Music News report on UMG and Sony expanding their Suno lawsuit to over 61,000 works.
Universal Music settles Udio lawsuit, strikes deal for licensed AI music platform (Music Business Worldwide)
Music Business Worldwide report on UMG settling with Udio and agreeing a licensed AI music platform.
UNI-1.1
by Luma AI
Luma AI announcement of the Uni-1.1 API for image generation.
Universal
Artificial Analysis speech-to-text page for AssemblyAI, covering Universal: word error rate, speed and price compared with other models.
VARCO 3D 2.0
by Top 3D AI
Top 3D AI listing for NC AI's VARCO 3D 2.0 generation tool with ratings.
VAST AI Research / Tripo
by Tripo AI
VAST AI Research hub: papers and code on generative 3D and world models behind Tripo.
Veo 3
by Google Cloud
Google Cloud Vertex AI API reference for Veo video generation models: request parameters and usage.
Veo 3.1 (Audio)
by Google
Google Developers blog post introducing Veo 3.1 and Veo 3.1 Fast video generation in the Gemini API.
SAM 2
Meta SAM 2 GitHub repo: code and notebooks for segmenting objects in images and video.
Vidu
Vidu: Shengshu's AI video generator for text prompts, images and reference videos.
Voxtral Mini
Artificial Analysis speech-to-text page for Mistral, covering Voxtral Mini: word error rate, speed and price compared with other models.
Voxtral Small
by Mistral AI
Mistral documentation page for Voxtral Small, its speech understanding model, with specs and API usage.
Wan 2.7
Alibaba Cloud announcement of Wan2.7-Video, a video generation model with editing and control features.
Wan2.7 image generation and editing API
Alibaba Cloud Model Studio API reference for Wan 2.7 Image and Image Pro: text-to-image, editing and multi-reference generation.
Wan 3.0
Alibaba Cloud announcement of Wan3.0, a video generation model producing 30-second clips from any input.
Wan (Alibaba Tongyi) video
by Wan
Wan-Video Wan2.1 GitHub repo: Alibaba's open large-scale video generation models.