User:Ftiercel

== Présentation ==

Artificial Intelligence State of Art
This section tries to keep up-to-date (2024-07-18) the best quality free artificial intelligence by feature:
 * From text
 * Text-to-Image: PixArt Sigma, Stable Diffusion 3 Medium, SDXL Flash, SDXL Turbo , SDXL 1.0
 * Text-to-Audio: Tango 2, Stable Audio, AudioGen , AudioLDM 2
 * Text-to-Music: MusicGen, JukeBox AI
 * Text-to-Video: Zeroscope v2, Open Sora, Modelscope
 * From image
 * Image-to-3D: Unique 3D, TripoSR, Instant Mesh
 * Image Upscaler: AuraSR, SUPIR, Ilaria
 * Image-to-Video: ExVideo, Stable Video Diffusion, Toon Crafter, AnimateDiff
 * Change viewpoint: Zero 1-to-3, CameraCtrl Stable Video Diffusion
 * From video
 * Video Upscaler: DiffIR2VR, Zeroscope XL
 * Video Soundifier: FoleyCrafter
 * Multimodal
 * Animate portrait: LivePortrait, Hallo, Dreamtalk