Models

398 matched .

Explore AI models for text, images, audio and coding. Filter by model task, open or closed weights, and Hugging Face availability.

Clear search and filters

All types Text · 2,080 Image · 398 Video · 224 Audio · 372 Coding · 40 Multimodal · 885 Structured data · 27 3D · 17

Most downloaded A–Z Recently synced

Hunyuan3D-Paint Tencent Hunyuan3D-Paint is Tencent’s text-to-3D painting and texture generation model. It takes existing 3D… Image · Open weights Open weights
HunyuanWorld 1.0 Tencent Tencent Hunyuan 3D, powered by the Hunyuan 3D Generate Large Model 2.5, is a 3D AI engine that turn… Image · Open weights Open weights
Ideogram 1.0 Ideogram AI AI model by Ideogram AI Image · Closed Closed weights
Ideogram 2.0 Ideogram AI AI model by Ideogram AI Image · Closed Closed weights
Ideogram 2a Ideogram AI AI model by Ideogram AI Image · Closed Closed weights
Ideogram 3 Ideogram AI Ideogram 3.0 is a text-to-image model built for design-grade typography and composition. It renders… Image · Closed Closed weights
Illusio Generative Suite Illusio is a creative enhancement mode that adds painterly texture and cohesive style. Image · Closed Closed weights
Image Playground Apple Image Playground is Apple’s on-device generative image tool inside Apple Intelligence. It creates p… Image · Closed Closed weights
Imagen Google AI model by Google Image · Closed Closed weights
Imagen 3 Google DeepMind Imagen 3 is Google’s latent diffusion text-to-image model for high-quality image generation from te… Image · Closed Closed weights
Imagen 3 Fast Imagen Imagen 3 Fast is the speed-optimized variant of Imagen 3. It delivers quick, high-quality text-to-i… Image · Closed Closed weights
Imagen 4 Google DeepMind Imagen 4 is Google’s advanced text-to-image model for photorealistic images, sharper clarity, impro… Image · Closed Closed weights
Imagen 4 Ultra Imagen Imagen 4 Ultra is a flagship text-to-image model for maximum fidelity. It excels at photorealism, c… Image · Closed Closed weights
Imagen 4.0 Fast Imagen Imagen 4 is Google Cloud’s latest family of Vertex AI text to image models that generate images fro… Image · Closed Closed weights
ImagineArt 2.0 ImagineArt ImagineArt 2.0 is ImagineArt’s latest proprietary image model, positioned as its top-tier option fo… Image · Closed Closed weights
Jasper Research 4B Jasper AI A 4.1B-parameter latent diffusion text-to-image model built by Jasper Research to validate the MONE… Image · Closed Closed weights
Kino XL Leonardo Interactive KIno XL targets a cinematic look with natural grain, film like color, and realistic lens behavior. Image · Closed Closed weights
Kollage by Kanana Naver Kollage by Kanana is Kakao’s multimodal creative model, designed for generating and combining diver… Image · Closed Closed weights
Latent Diffusion CompVis Latent Diffusion by CompVis is a text to image method that runs the diffusion process in a compress… Image · Open weights Open weights
Leonardo Phoenix Leonardo Interactive AI model by Leonardo Interactive Image · Closed Closed weights
Leonardo Phoenix 0.9 Leonardo Interactive Phoenix 0.9 is an earlier Phoenix release known for flexible style and fast iteration. Image · Closed Closed weights
Leonardo Phoenix 1.0 Leonardo Interactive Phoenix 1.0 is a foundation image model focused on prompt adherence, detail, and iterative editing. Image · Closed Closed weights
LingBot Vision Giant Robbyant LingBot-Vision-Giant is a ViT-g/16 self-supervised Vision Transformer backbone for dense visual per… Image · Open weights Open weights
LingBot Vision Small Robbyant LingBot-Vision-Small is a lightweight Vision Transformer (ViT-S/16) backbone pretrained with self-s… Image · Open weights Open weights
Lucid Origin Leonardo Interactive Lucid Origin is a versatile text-to-image model for vivid concepts, clean composition, and reliable… Image · Closed Closed weights
Lucid Realism Leonardo Interactive Lucid Realism is a photoreal image model tuned for natural lighting, skin detail, and believable ma… Image · Open weights Open weights
Lumiere Google AI model by Google Image · Closed Closed weights
MAI Image 1 Microsoft Latent Diffusion by CompVis is a text to image method that runs the diffusion process in a compress… Image · Closed Closed weights
MAI Image 2 Microsoft MAI-Image-2 is Microsoft’s second-generation text-to-image model built for creative work, emphasizi… Image · Closed Closed weights
MAI Image 2.5 Microsoft MAI-Image-2.5 is Microsoft AI’s image model for text-to-image generation and image editing with str… Image · Closed Closed weights
MAI Image 2.5 Flash Microsoft MAI-Image-2.5 Flash is Microsoft AI’s ultra-efficient variant of MAI-Image-2.5 for lower-cost image… Image · Closed Closed weights
MAI-Image-2.5-Pro Microsoft Text-to-image generation and image-to-image editing model from Microsoft. Uses a diffusion-based ap… Image · Closed Closed weights
Make-A-Scene Meta Platforms AI model by Meta Platforms Image · Closed Closed weights
Midjourney 5.1 Midjourney Midjourney 5.1 improves prompt fidelity, realism, and control over composition and lighting. Image · Closed Closed weights
Midjourney 5.2 Midjourney Midjourney 5.2 sharpens detail and responsiveness further, with better variation control for iterat… Image · Closed Closed weights
Midjourney V1 Midjourney Midjourney V1 introduced the platform’s signature stylized look, good for striking, painterly compo… Image · Closed Closed weights