ndreca/hunyuan3d-2
Generate textured 3D meshes from a single image. Convert a single-view photo into a high-resolution 3D asset using diffu...
Found 57 models (showing 41-57)
Generate textured 3D meshes from a single image. Convert a single-view photo into a high-resolution 3D asset using diffu...
Generate 3D Gaussian-splat assets from a text prompt. Outputs a PLY point cloud suitable for rendering or downstream 3D...
Generate expressive in-game dialogue portraits from a reference character image and a text prompt. Produce consistent ch...
Generate 3D meshes from a single input image. Accepts an image (ideally with a clean or transparent background) and reco...
Generate textured 3D assets from a single image. Takes an object photo (front-facing recommended) and outputs a textured...
Texture 3D meshes from a text prompt. Provide a 3D shape file (.obj or .off) and a textual description; the model return...
Create an interactive, cursor-following face from a single face image. Provide one face image as input and receive indiv...
Create cursor-following face interactions for the web from a single face image. Input a face image and optional controls...
Generate pixel-art tilesets, tiles, and map objects from text prompts and optional reference images. Use modes for diffe...
Generate pixel-art images and game assets from a text prompt or an input image. Support image-to-image with a strength c...
Generate animated pixel art sprites and spritesheets from a text prompt, with optional reference image guidance. Produce...
Generate 3D models from text prompts and up to five reference images. Produce geometry and textures as a 3D asset in glb...
Generate expressive character portrait sheets for game dialogs from a reference image and a text prompt. Take an input c...
Generate seamless, tileable PBR texture maps from a text prompt. Outputs diffuse (albedo), normal, roughness, and ambien...
Generates detailed SVG vector graphics from text prompts with enhanced geometric precision and finer paths compared to s...
Generates music for games conditioned on emotion from text prompts. Supports audio input for melody mimicry or continuat...
Generates videos from text prompts with full alpha channel support for transparent backgrounds. Outputs WebM or WebP for...