AI Models

Explore 71+ AI models for text, image, video, audio, and 3D generation. Compare capabilities, pricing tiers, and find the perfect model for your needs.

Showing 23 of 71 models

PhotoMaker
face-generation Standard

PhotoMaker

TencentARC (via Replicate)

Create photos of a person in various styles while preserving their identity.

Pika 2.2
Video Standard

Pika 2.2

Pika Labs (via Fal.ai)

Popular video generation model known for creative effects and image animation.

Creative video effects

PixVerse 5.5
Video Standard

PixVerse 5.5

PixVerse (via Fal.ai)

Creative video generation model. Great for artistic and stylized video content.

Professional Headshot
face-generation Standard

Professional Headshot

flux-kontext-apps (via Replicate)

Transform casual photos into professional studio-quality headshots.

Instant pro headshots

Recraft V3
Image Standard

Recraft V3

Recraft (via Replicate)

Specialized in vector-style and design-focused images.

Vector & design focused

Recraft V3 SVG
Image Standard

Recraft V3 SVG

Recraft (via Replicate)

Generate scalable vector graphics (SVG) from text prompts.

Riverflow 2.0 Fast
Image Standard

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

SAM 2
segmentation Standard

SAM 2

Meta (via Fal.ai)

Segment Anything Model 2 - segment any object in images or videos with prompts.

Segment anything

SDXL ControlNet Union
controlnet Standard

SDXL ControlNet Union

Fal.ai

Multiple control types in one model: canny, depth, pose, segmentation, and more.

All-in-one ControlNet

Seedream 4
Image Standard

Seedream 4

ByteDance (via Replicate)

Text-to-image and single-sentence editing at up to 4K resolution.

Speech 02 Turbo
TTS Standard

Speech 02 Turbo

MiniMax (via Replicate)

Fast text-to-speech variant of Speech 02 optimized for speed.

Stable Diffusion 3
Image Standard

Stable Diffusion 3

Stability AI (via Replicate)

Latest Stable Diffusion with improved text rendering and composition.

SwinIR
image-restoration Standard

SwinIR

jingyunliang (via Replicate)

General image restoration: denoising, deblurring, and super-resolution.

Sync Lipsync V2
Video Standard

Sync Lipsync V2

Fal.ai

Advanced lipsync technology for realistic talking videos.

Trellis
3D Standard

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

Veo 3.1 Fast
Video Standard

Veo 3.1 Fast

Google (via Fal.ai)

Faster version of Veo 3.1 optimized for quick video generation with good quality.

Wan 2.2 Image-to-Video
Video Standard

Wan 2.2 Image-to-Video

Alibaba (via Fal.ai)

Alibaba's image-to-video model. Efficient and reliable video generation from images.

Wan 2.5 Image-to-Video
Video Standard

Wan 2.5 Image-to-Video

Wan Video (via Replicate)

Animate images into videos with natural motion and high fidelity.

Wan 2.5 Text-to-Video
Video Standard

Wan 2.5 Text-to-Video

Wan Video (via Replicate)

High-quality text-to-video generation with smooth motion.

Whisper
speech-to-text Standard

Whisper

OpenAI (via Fal.ai)

OpenAI Whisper large v3 for accurate speech transcription and translation. Supports 99+ languages.

Accurate speech transcription

Wizper
speech-to-text Standard

Wizper

Fal.ai

Optimized Whisper v3 by Fal.ai - same accuracy, 2x faster performance.

2x faster Whisper

Wonder3D
3D Standard

Wonder3D

adirik (via Replicate)

Image-to-3D with realistic mesh generation. Outputs textured .glb files.

XTTS-v2
voice-cloning Standard

XTTS-v2

Coqui (via Replicate)

Clone any voice with just 6 seconds of audio. Supports 17 languages.

Clone voices in seconds