AI Models
Explore 131+ AI models for text, image, video, audio, and 3D generation. Compare capabilities, pricing tiers, and find the perfect model for your needs.
Showing 24 of 131 models
Recraft V3
Recraft (via Replicate)
Specialized in vector-style and design-focused images.
Vector & design focused
Recraft V3 SVG
Recraft (via Replicate)
Generate scalable vector graphics (SVG) from text prompts.
Riverflow 2.0 Fast
Sourceful (via Replicate)
Agentic image generation model with font control, transparent backgrounds, and image editing capabilities.
Agentic image gen with typography
Rodin
Hyper3D (via Replicate)
Generate 3D models from text or images. Create game assets and 3D content.
3D model generation
SAM 2
Meta (via Fal.ai)
Segment Anything Model 2 - segment any object in images or videos with prompts.
Segment anything
SAM 3 3D Body
Fal.ai
Accurate 3D reconstruction of human body shape from images.
SAM 3 3D Objects
Fal.ai
Accurate 3D reconstruction of objects from real images.
Sana
Fal.ai
Fast and lightweight image generation model optimized for speed.
SDXL
Stability AI (via Replicate)
Stable Diffusion XL. Reliable baseline for image generation.
SDXL ControlNet Union
Fal.ai
Multiple control types in one model: canny, depth, pose, segmentation, and more.
All-in-one ControlNet
Seedream 4
ByteDance (via Replicate)
Text-to-image and single-sentence editing at up to 4K resolution.
Seedream 4.5
ByteDance (via Replicate)
ByteDance's unified image generation and editing model. Supports up to 4K resolution.
Shap-E
OpenAI (via Replicate)
OpenAI fast 3D generation from text or images. Quick prototyping and ideation.
Sora 2
OpenAI (via Fal.ai)
OpenAI's flagship video generation model. Creates high-quality, realistic videos from text prompts.
OpenAI's flagship video AI
Sora 2 Image-to-Video
OpenAI (via Fal.ai)
Animate images into videos using Sora 2. Transform still images into dynamic video content.
Speech 02 HD
MiniMax (via Replicate)
High-definition text-to-speech with premium voice quality.
Speech 02 Turbo
MiniMax (via Replicate)
Fast text-to-speech variant of Speech 02 optimized for speed.
Stable Diffusion 3
Stability AI (via Replicate)
Latest Stable Diffusion with improved text rendering and composition.
Stable Diffusion 3.5 Large
Stability AI (via Replicate)
Latest Stable Diffusion with 8B parameters. Superior quality and prompt understanding.
SwinIR
jingyunliang (via Replicate)
General image restoration: denoising, deblurring, and super-resolution.
Sync Lipsync V2
Fal.ai
Advanced lipsync technology for realistic talking videos.
Text Extract OCR
abiruyt (via Replicate)
Simple, versatile text extraction from any image.
Trellis
Microsoft (via Fal.ai)
Native 3D generative model using Structured LATents (SLAT) for versatile, high-quality 3D asset creation from images.
SLAT-based 3D generation
Tripo3D
Tripo (via Fal.ai)
Fast, affordable image-to-3D with clean meshes and PBR texture support.
Fast & affordable 3D