Models Guide

65 models

Explore complete guides for all our AI models. Learn capabilities, best practices, and tips for each model.

Alibaba

(14 models)
Wan 2.6
Alibabavideo

Alibaba Wan 2.6 text-to-video with 5/10/15s output, 720p/1080p tiers

Read Guide
Wan 2.6
Alibabavideo

Alibaba Wan 2.6 image-to-video with 5/10/15s output, 720p/1080p tiers

Read Guide
Wan 2.6
Alibabavideo

Alibaba Wan 2.6 video-to-video with 5/10s output, 720p/1080p tiers

Read Guide
Wan 2.7
Alibabavideo

Alibaba Wan 2.7 text-to-video (720p/1080p, 2–15s) with optional audio-driven generation and prompt extension

Read Guide
Wan 2.7
Alibabavideo

Alibaba Wan 2.7 image-to-video with first/last-frame conditioning, optional driving audio, 720p/1080p, 2–15s

Read Guide
Wan 2.7
Alibabavideo

Alibaba Wan 2.7 reference-to-video: generate a video conditioned on up to 5 reference images/videos, 720p/1080p, 2–10s

Read Guide
Wan 2.7
Alibabavideo

Alibaba Wan 2.7 video editing — modify an input video with a prompt and optional reference image, 720p/1080p, 2–10s

Read Guide
Wan Animate Replace
Alibabavideo

Replace characters in video while preserving motion

Read Guide
Wan 2.7 Image
Alibabaimage

Versatile image generation and editing with thinking mode for enhanced quality

Read Guide
Wan 2.7 Image Pro
Alibabaimage

Pro-quality image generation with 4K output and enhanced detail

Read Guide
HappyHorse 1.0
Alibabavideo

Generate 720P or 1080P video from a text prompt. Supports flexible aspect ratios and durations from 3 to 15 seconds.

Read Guide
HappyHorse 1.0
Alibabavideo

Animate a reference image into a 720P or 1080P video with optional text guidance.

Read Guide
HappyHorse 1.0
Alibabavideo

Generate video from 1–9 reference images and a text prompt. Supports 720P or 1080P and flexible aspect ratios.

Read Guide
HappyHorse 1.0
Alibabavideo

Edit a video with text instructions and optional reference images. Supports 720P or 1080P output.

Read Guide

Black Forest Labs

(4 models)
Flux 2 Pro
Black Forest Labsimage

High-quality photorealistic image generation by Black Forest Labs

Read Guide
Flux 2 Pro
Black Forest Labsimage

Multi-image input — combine and transform up to 8 images with AI

Read Guide
Flux 2 Flex
Black Forest Labsimage

Flexible photorealistic image generation by Black Forest Labs

Read Guide
Flux 2 Flex
Black Forest Labsimage

Multi-image transformation with flexible composition (up to 8 source images)

Read Guide

Bytedance

(12 models)
OmniHuman 1.5
Bytedancevideo

Turn a portrait photo and an audio clip into a lifelike talking video with natural motion and accurate lip sync

Read Guide
Seedance 1.5 Pro
Bytedancevideo

ByteDance Seedance 1.5 Pro for text/image-conditioned video with cinematic camera control and optional audio

Read Guide
Seedance 2.0
Bytedancevideo

ByteDance Seedance 2.0 — next-gen text/image/video-conditioned video generation with synced audio, up to 15s, 4K

Read Guide
Seedance 2.0 Fast
Bytedancevideo

ByteDance Seedance 2.0 Fast — quicker, lower-cost variant of Seedance 2.0 (up to 720p, 15s). Supports text/image/video-to-video.

Read Guide
Seedance 2.0 Mini
Bytedancevideo

ByteDance Seedance 2.0 Mini — compact, budget-friendly variant of Seedance 2.0 (up to 720p, 15s). Supports text/image/video-to-video.

Read Guide
Seedream 5.0 Lite
Bytedanceimage

Unified multimodal text-to-image generation with improved consistency and up to 3K output

Read Guide
Seedream 5.0 Lite
Bytedanceimage

Unified multimodal image editing with improved consistency and up to 3K output

Read Guide
Seedream 4.0 Edit
Bytedanceimage

Edit and transform images with up to 10 reference images using Seedream 4.0

Read Guide
Seedream 4.5
Bytedanceimage

Refined Seedream 4.5 text-to-image generation with up to 4K output and stronger prompt consistency

Read Guide
Seedream 4.5 Edit
Bytedanceimage

Refined Seedream 4.5 image editing with up to 4K output and stronger instruction following

Read Guide
Seedream 5.0 Pro
Bytedanceimage

Flagship Seedream 5.0 Pro text-to-image generation with strong prompt adherence, up to 2K output

Read Guide
Seedream 5.0 Pro
Bytedanceimage

Flagship Seedream 5.0 Pro image editing with strong instruction following, up to 2K output

Read Guide

ElevenLabs

(5 models)
ElevenLabs TTS Turbo 2.5
ElevenLabsmusic

Ultra-fast, natural text-to-speech

Read Guide
ElevenLabs Dialogue V3
ElevenLabsmusic

Generate multi-speaker dialogue with per-line voice selection and previewable ElevenLabs voices

Read Guide
ElevenLabs Speech to Text
ElevenLabsmusic

Scribe v1 speech-to-text with multilingual transcription, diarization, and audio-event tagging

Read Guide
ElevenLabs Multilingual V2
ElevenLabsmusic

Multilingual text-to-speech with natural voice cloning

Read Guide
ElevenLabs Sound FX V2
ElevenLabsmusic

Generate sound effects from text descriptions

Read Guide

Google

(9 models)
Gemini Omni
Googlevideo

Google Gemini Omni — natural-language video generation with native audio. Optional reference images, source clip, voices, and characters. Tier prices by resolution × duration.

Read Guide
Gemini Omni
Googlevideo

Google Gemini Omni — animate reference images into video with native audio. Optional source clip, voices, and characters. Tier prices by resolution × duration.

Read Guide
Gemini Omni
Googlevideo

Google Gemini Omni — edit/extend a source video with native audio. Optional reference images, voices, and characters. Flat price per generation by output resolution (duration auto-detected).

Read Guide
Google Imagen 4
Googleimage

High-quality text-to-image generation with strong detail and creative versatility

Read Guide
Google Imagen 4 Fast
Googleimage

Fast high-quality text-to-image generation with strong detail and creative versatility

Read Guide
Google Imagen 4 Ultra
Googleimage

Highest-fidelity Imagen 4 generation with maximum detail and prompt adherence

Read Guide
Nano Banana 2
Googleimage

Google Gemini 3.1 Flash Image with fast generation, strong text rendering, and consistent characters

Read Guide
Nano Banana 2 Lite
Googleimage

Lightweight, low-cost Nano Banana 2 variant for fast everyday image generation and editing

Read Guide
Nano Banana Pro
Googleimage

Advanced image generation and editing with up to 8 reference images, 4K output

Read Guide

Infinitalk

(1 model)
Infinitalk
Infinitalkvideo

Generate a talking-head video from a photo and an audio track with natural lip sync

Read Guide

Invoomen

(2 models)
Invoomen Lip-Sync
Invoomenvideo

Re-sync any video's lips to a new audio track — swap dialogue, dub, or voice-over while keeping the original footage

Read Guide
Invoomen Video Beta
Invoomenvideo

Turn an idea or script into a narrated short video with matching stock footage, voiceover, and subtitles.

Read Guide

Kling

(10 models)
Kling AI Avatar
Klingvideo

Create lifelike talking avatars from a photo and audio with accurate lip sync and prompt control

Read Guide
Kling AI Avatar Pro
Klingvideo

Create lifelike talking avatars from a photo and audio with enhanced quality and accurate lip sync

Read Guide
Kling Motion Control 3.0
Klingvideo

Transfer motion from a reference video onto a character image while preserving identity, expressions, and natural dynamics

Read Guide
Kling V2.5 Turbo
Klingvideo

Kling 2.5 Turbo text-to-video with improved prompt adherence, fluid motion, and realistic physics

Read Guide
Kling V2.5 Turbo
Klingvideo

Kling 2.5 Turbo image-to-video with strong prompt adherence, smooth motion, and realistic physics

Read Guide
Kling 2.6
Klingvideo

Kling 2.6 text-to-video with optional synchronized audio generation

Read Guide
Kling 2.6
Klingvideo

Kling 2.6 image-to-video with optional synchronized audio generation

Read Guide
Kling 3.0
Klingvideo

Generate high-quality videos with advanced multi-shot capabilities and element references using Kling 3.0.

Read Guide
Kling 3.0 Turbo
Klingvideo

Kling 3.0 Turbo text-to-video — faster generation with strong motion quality at up to 1080p

Read Guide
Kling 3.0 Turbo
Klingvideo

Kling 3.0 Turbo image-to-video — animate an image quickly with strong motion quality at up to 1080p

Read Guide

OpenAI

(2 models)
GPT Image 2
OpenAIimage

OpenAI GPT Image 2 text-to-image generation — high prompt fidelity with 11 aspect ratio options

Read Guide
GPT Image 2
OpenAIimage

OpenAI GPT Image 2 image-to-image — transform or reference one or more input images with a prompt

Read Guide

Qwen

(1 model)
Z-Image
Qwenimage

Efficient photorealistic image generation with fast performance and accurate bilingual text rendering

Read Guide

xAI

(5 models)
Grok Imagine
xAIvideo

xAI Grok Imagine text-to-video with configurable aspect ratio, mode, duration, and resolution

Read Guide
Grok Imagine
xAIvideo

xAI Grok Imagine image-to-video with mode, duration, and resolution controls

Read Guide
Grok Imagine 1.5
xAIvideo

xAI Grok Imagine 1.5 — sharper motion and stronger prompt adherence, from text or a reference image

Read Guide
Grok Imagine
xAIimage

xAI's fast image generation with a standard mode and a higher-accuracy quality mode

Read Guide
Grok Imagine
xAIimage

Transform images with Grok's powerful AI — style transfer and editing

Read Guide