Model library

Model depth for creator workflows

Compare model strengths, output styles, and app compatibility so each project starts with the right engine.

29 models

Across image, video, and audio tasks.

7 categories

Pick by outcome, not guesswork.

Scribe V2

Speech to Text

ElevenLabs speech-to-text for transcripts, subtitles, captions, and long-form audio cleanup.

By ElevenLabs · First announced: March 3, 2025

Speech to Text
Learn more

Chatterbox

Audio Generation

Reference-audio text-to-speech for cloning delivery style, creator narration, and character-driven voice work.

By Resemble AI · First announced: June 2, 2025

Text to Speech
Learn more

Eleven v3

Audio Generation

Expressive ElevenLabs speech generation for dialogue-heavy reads, emotional narration, and polished voice work.

By ElevenLabs · First announced: August 20, 2025

Text to Speech
Learn more

ElevenLabs Turbo v2.5

Audio Generation

Fast ElevenLabs text-to-speech for narration, captions, and practical production voice work.

By ElevenLabs · First announced: June 17, 2025

Text to Speech
Learn more

MiniMax Music 2.0

Audio Generation

MiniMax’s lyric-driven music generation model for songs, hooks, and prompt-based audio production.

By MiniMax · First announced: October 31, 2025

Text to Music
Learn more

Grok Imagine Image

Image Generation

xAI’s image model for fast generation, iterative edits, and multi-style prompt workflows.

By xAI · First announced: January 28, 2026

Text to Image
Learn more

Nano Banana

Image Generation

Google’s original Nano Banana image model for fast prompt-based image generation at lower per-image cost.

By Google DeepMind · First announced: October 2, 2025

Text to Image
Learn more

Nano Banana 2

Image Generation

Fast image generation and editing model for practical creative iteration and production workflows.

By Google DeepMind · First announced: November 20, 2025

Text to Image
Learn more

Nano Banana Pro

Image Generation

Google DeepMind’s Gemini 3 Pro Image model focused on high-fidelity generation and editing.

By Google DeepMind · First announced: November 20, 2025

Text to Image
Learn more

Z Image Base

Image Generation

Tongyi-MAI’s balanced Z Image foundation model for prompt-faithful generation across a broad range of styles.

By Tongyi-MAI · First announced: 2025

Text to Image
Learn more

Z Image Turbo

Image Generation

Tongyi-MAI’s fast image model for low-latency, cost-efficient text-to-image generation.

By Tongyi-MAI · First announced: 2025

Text to Image
Learn more

Seedream 5 Lite

Image Generation

ByteDance Seed’s image creation model emphasizing stronger understanding and reasoning.

By ByteDance Seed · First announced: February 13, 2026

Text to Image
Learn more

Recraft V4

Image Generation

Design-first image model tuned for brand, marketing, and creative production workflows.

By Recraft · First announced: February 17, 2026

Text to Image
Learn more

Recraft V4 Pro

Image Generation

Design-first image model tuned for brand, marketing, and creative production workflows.

By Recraft · First announced: February 17, 2026

Text to Image
Learn more

FLUX.2 [pro]

Image Generation

Black Forest Labs’ production FLUX.2 model optimized for high-quality generation at speed.

By Black Forest Labs · First announced: November 25, 2025

Text to Image
Learn more

FLUX.2 [dev]

Image Generation

Developer-focused FLUX.2 variant for flexible experimentation and iterative visual workflows.

By Black Forest Labs · First announced: November 25, 2025

Text to Image
Learn more

Grok Imagine Image Edit

Image Editing

xAI’s prompt-based editing model for targeted image updates with support for multiple references.

By xAI · First announced: January 28, 2026

Magic Edit
Learn more

Nano Banana Edit

Image Editing

Google’s original Nano Banana editing workflow for prompt-based updates using one or more reference images.

By Google DeepMind · First announced: October 2, 2025

Magic Edit
Learn more

Nano Banana 2 Edit

Image Editing

Fast prompt-based image editing workflow for controlled updates using one or more reference images.

By Google DeepMind · First announced: November 20, 2025

Magic Edit
Learn more

Nano Banana Pro Edit

Image Editing

Editing workflow based on Google DeepMind’s Nano Banana Pro image generation and editing model.

By Google DeepMind · First announced: November 20, 2025

Magic Edit
Learn more

Seedream 5 Lite Edit

Image Editing

ByteDance’s fast Seedream 5 Lite editing workflow for multi-reference prompt-based image updates.

By ByteDance Seed · First announced: February 13, 2026

Magic Edit
Learn more

FLUX.1 Kontext [pro]

Image Editing

Black Forest Labs’ context-aware editing model for fast iterative image transformations.

By Black Forest Labs · First announced: May 29, 2025

Magic Edit
Learn more

Grok Imagine Video

Video Generation

xAI’s video generation model for prompt-based scene animation and edit-style iteration.

By xAI · First announced: January 28, 2026

Image to Video
Learn more

Veo 3.1

Video Generation

Google DeepMind’s Veo 3.1 model family for expressive video generation with stronger control.

By Google DeepMind · First announced: October 15, 2025

Image to Video
Learn more

Veo 3.1 Fast

Video Generation

A faster Veo 3.1 path for teams optimizing turnaround while keeping strong output quality.

By Google DeepMind · First announced: October 15, 2025

Image to Video
Learn more

Wan 2.5

Video Generation

Alibaba Cloud’s Wan visual-generation line, exposed here as a preview image-to-video workflow.

By Alibaba Cloud · First announced: September 24, 2025

Image to Video
Learn more

SeedVR2 Upscale

Image Upscaling

Image upscaling route based on ByteDance Seed’s SeedVR restoration research line.

By ByteDance Seed · First announced: March 22, 2025

Image Upscale
Learn more

Topaz Upscale

Image Upscaling

Topaz Labs enhancement workflow for high-quality image upscaling and detail restoration.

By Topaz Labs · First announced: Public date not specified

Image Upscale
Learn more

SeedVR2 Video Upscale

Video Upscaling

Video restoration and upscale path built from the SeedVR research family and provider runtimes.

By ByteDance Seed · First announced: March 22, 2025

Video Upscale
Learn more