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

Kling Video 2.6
Video Standard

Kling Video 2.6

Kuaishou (via Fal.ai)

Advanced video generation model from Kuaishou. Known for excellent character consistency and motion quality.

Consistent character video

Kling Video Image-to-Video
Video Standard

Kling Video Image-to-Video

Kuaishou (via Fal.ai)

Transform images into videos with Kling. Excellent at maintaining character and scene consistency.

Kokoro 82M
TTS Budget

Kokoro 82M

Jaaari (via Replicate)

Lightweight 82M parameter text-to-speech model with natural voices.

LaTeX OCR
ocr Budget

LaTeX OCR

mickeybeurskens (via Replicate)

Convert math equation images directly to LaTeX code.

LongCat Image
Image Standard

LongCat Image

Fal.ai

6B parameter model excelling at multilingual text rendering, photorealism, and deployment efficiency.

LTX-2
Video Budget

LTX-2

Lightricks (via Fal.ai)

Fast and affordable video generation model. Good balance of quality and cost for everyday use.

Fast & affordable video

LTX-2 Image-to-Video
Video Budget

LTX-2 Image-to-Video

Lightricks (via Fal.ai)

Animate images with LTX-2. Quick and cost-effective image-to-video generation.

Lyria 2
Audio Premium

Lyria 2

Google (via Replicate)

Google's advanced music generation model for creating original compositions.

Google's AI music composer

Marigold Depth
depth-estimation Standard

Marigold Depth

Replicate

Diffusion-based depth estimation with fine details and sharp edges.

Marker
ocr Standard

Marker

cuuupid (via Replicate)

Convert PDF, EPUB, and documents to clean Markdown or JSON.

PDF to Markdown

Maya TTS
TTS Standard

Maya TTS

Fal.ai

State-of-the-art speech model for expressive voice generation.

Expressive voice generation

Meshy
3D Standard

Meshy

Meshy (via Fal.ai)

Complete 3D pipeline: text/image-to-3D with remeshing, retexturing, and rigging capabilities.

Complete 3D pipeline

MiniMax Music V2
Audio Standard

MiniMax Music V2

MiniMax (via Fal.ai)

Generate original music tracks from text descriptions.

Music 1.5
Audio Standard

Music 1.5

MiniMax (via Replicate)

Generate royalty-free music tracks from text descriptions.

MVDream
3D Standard

MVDream

ByteDance (via Replicate)

Multi-view diffusion for 3D generation from text. Creates consistent 3D assets from descriptions.

Nano Banana Pro
Image Standard

Nano Banana Pro

Fal.ai

Fast and efficient image generation model. Excellent quality-to-speed ratio for rapid prototyping and production use.

Fast & efficient image gen

OmniHuman 1.5
Video Premium

OmniHuman 1.5

ByteDance (via Fal.ai)

Advanced human generation and animation model.

OpenVoice
voice-cloning Standard

OpenVoice

MyShell (via Replicate)

Instant voice cloning with fine-grained control over style, emotion, and accent.

Parler TTS
TTS Standard

Parler TTS

Replicate

Describe the voice you want in text. Generate speech matching your description.

Photo Restoration
image-restoration Standard

Photo Restoration

Fal.ai

Restore old or damaged photos. Fix colors, remove scratches, enhance resolution.

Restore old photos

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