Categoria
Todos os Modelos
159 Modelos
Text to ImageSeedream 4.5
ByteDance's flagship text-to-image model with exceptional photorealism.
Text to ImageSeedream 5.0 Lite
Latest Seedream with 2K/3K resolution and PNG output support.
Text to ImageSeedream 4.0
High-performance image generation with excellent quality.
Text to ImageSeedream 3.0
Cost-effective image generation with good quality.
WAN 2.1
Efficient video generation with good motion quality from Alibaba.
WAN 2.5
Latest WAN model with improved quality and motion coherence.
WAN 2.6
Latest WAN model with enhanced motion and longer durations.
WAN 2.2 Text-to-Video
Efficient video generation with good motion.
Text to ImageFlux Dev
High-quality image generation with excellent prompt following.
Text to ImageFlux Schnell
Ultra-fast image generation for rapid prototyping.
Sora 2
OpenAI's flagship video generation model.
Sora 2 Pro
Premium Sora model with enhanced quality.
Google Veo 3.1
Google's flagship video generation model.
Google Veo 3.1 Fast
Fast Google video generation.
Google Veo 3
High-quality Google video generation.
Google Veo 3 Fast
Fast Google video generation.
Google Veo 2
Reliable Google video generation.
Seedance 1.5 Pro
Latest Seedance with enhanced motion and frame control.
Seedance 1.0 Pro
Premium Seedance with enhanced quality.
Seedance 1.0 Pro Fast
Pro quality with fast generation.
Seedance 1.0 Lite
Lightweight Seedance for rapid generation.
Vidu Q2
High-quality video generation from Vidu.
Vidu Q1
Fast and efficient 1080p video generation.
Kling v1
Original Kling model with reliable quality.
Kling v1.5
Improved Kling with better motion coherence.
Kling v1.6
Latest v1 series with enhanced quality.
Kling O1
Reference-based video with multi-image support.
Kling v2 Master
Premium v2 with cinematic quality.
Kling v2.1
Balanced speed and fidelity for v2 series.
Kling v2.1 Master
Premium v2.1 with highest quality.
Kling v2.5 Turbo
Fast generation with good quality.
Kling v2.6
Latest Kling with audio generation.
Kling v3.0 Standard
Next-gen Kling with improved quality and audio.
Kling v3.0 Standard
Next-gen Kling image-to-video with audio.
Kling v3.0 Pro
Premium next-gen Kling with highest quality.
Kling v3.0 Pro
Premium next-gen Kling image-to-video.
Kling Lipsync
Add lip-synced speech to any video.
Kling v1 Image-to-Video
Animate images with v1 quality.
Kling v2 Master Image-to-Video
Premium image animation with cinematic quality.
Hailuo 2.3
High-quality video generation with natural motion.
Text to ImageZ-Image
Fast and affordable text-to-image generation.
Text to ImageGPT Image
OpenAI's flagship image generation model.
Image to ImageGPT Image
OpenAI's image transformation model.
Text to ImageGPT Image 1.5
OpenAI's latest image model with enhanced capabilities.
Image to ImageGPT Image 1.5
OpenAI's latest image editing model.
Image to ImageGPT Image 1 Mini
OpenAI's budget-friendly image editing model.
Text to ImageGrok Imagine Image
xAI's creative and versatile image generation model.
Image to ImageGrok Imagine Image
xAI's creative image editing model.
Text to ImageNano Banana Pro
Strongest prompt-following model with exceptional detail.
Text to ImageNano Banana 2
Pro quality at Flash speed with 4K and PNG support.
Image to ImageNano Banana Pro
Image transformation with strongest prompt following.
Image to ImageNano Banana 2
Image transformation at Flash speed with multi-reference support.
Text to ImageNano Banana
Ultra-high character consistency at affordable price.
Image to ImageNano Banana
Image transformation with character consistency.
Text to ImageQwen Image
Great at complex text rendering in images.
Image to ImageQwen Image
Image transformation with text rendering capability.
Text to ImageWAN 2.2
Fast and creative image generation.
Text to ImageWAN 2.5
Photorealism and creative control for image generation.
Image to ImageWAN 2.5
Photorealistic image transformation.
Text to ImageFlux Dev Lora
General art and design with LoRA support.
Text to ImageFlux Kontext Pro
Consistent, in-context image generation.
Image to ImageFlux Kontext Pro
Context-aware image transformation.
Text to ImageFlux Kontext Max
Maximum context for detailed scenes.
Image to ImageFlux Kontext Max
Maximum context for complex image edits.
Text to ImageFlux 2
Next-gen Flux with improved quality.
Image to ImageFlux 2
Next-gen image transformation.
Text to ImageFlux 2 Pro
Premium Flux 2 with highest quality.
Image to ImageFlux 2 Pro
Premium image transformation.
Text to ImageFlux 2 Flex
Flexible generation at lower cost.
Image to ImageFlux 2 Flex
Flexible image transformation.
Image to ImageSeedream 4.0
Image transformation with cohesive styles.
Image to ImageSeedream 4.5
Image transformation with enhanced quality.
Image to ImageSeedream 5.0 Lite
Image transformation with 2K/3K and multi-reference input.
Image to ImageSeedEdit 3.0
Advanced image editing with precise control.
Image to ImageSeedream 4.0 Edit Sequential
Batch edit multiple images with consistent style.
Image to ImageSeedream 4.5 Edit Sequential
Premium batch editing with enhanced quality.
Text to ImageSeedream 5.0 Lite Edit Sequential
Batch text-to-image with 2K/3K and PNG support.
Image to ImageSeedream 5.0 Lite Edit Sequential
Batch image generation with 2K/3K and PNG support.
Hailuo 2.3 Fast
Fast image-to-video with natural motion.
Hailuo 2.3
High quality image-to-video animation.
Hailuo 2.3 Pro
Premium text-to-video with enhanced quality.
Hailuo 02
High-quality text-to-video with frame control.
Hailuo 02 (First/Last Frame)
First/Last frame to video.
T2V-01
Affordable text-to-video generation.
T2V-01 Director
Text-to-video with camera control.
I2V-01
Image-to-video with natural motion.
I2V-01 Director
Image-to-video with camera control.
I2V-01 Live
Live-action style image animation.
S2V-01
Subject-driven video generation.
Text to MusicMusic 2.0
AI music generation from text prompts and lyrics.
Text to MusicMusic 2.5
Next-gen AI music generation with high-fidelity audio.
Text to AudioSpeech 2.6 HD
Latest HD TTS with outstanding prosody.
Text to AudioSpeech 2.6 Turbo
Fast TTS with 40 language support.
Text to AudioSpeech 02 HD
Superior rhythm and voice quality.
Text to AudioSpeech 02 Turbo
Fast TTS with enhanced multilingual.
WAN 2.5
Image-to-video with A/V sync.
WAN 2.6
Image-to-video with enhanced motion.
WAN 2.5 Video Extend
Extend videos with AI-generated continuation.
ByteDance Video Upscaler
AI super-resolution video upscaling to 4K.
Seedance 1.5 Pro Video Extend
Extend videos with natural motion and stable aesthetics.
Seedance 1.5 Pro Video Extend Fast
Extend videos with natural motion continuation.
Seedance 1.5 Pro
Latest image-to-video with enhanced motion.
Seedance 1.0 Pro
Premium image-to-video animation.
Seedance 1.0 Pro Fast
Pro quality image-to-video with fast generation.
Seedance 1.0 Lite
Lightweight image-to-video with frame control.
Sora 2
OpenAI image-to-video with audio.
Sora 2 Pro
Premium OpenAI image-to-video.
Google Veo 3.1
Google image-to-video with frame support.
Google Veo 3.1 Fast
Fast Google image-to-video.
Grok Imagine Video
xAI's creative and flexible video generation model.
Grok Imagine Video
xAI's creative image-to-video animation.
Grok Imagine Video Edit
xAI's prompt-driven video editing model.
Runway Gen4 Turbo
High-quality image-to-video with cinematic motion.
Runway Gen4 Aleph
Transform videos with natural language editing.
Runway Upscale V1
4X AI video upscaling with enhanced details.
Vidu Q2
Vidu image-to-video with audio.
Text to AudioEleven V3
Most expressive TTS model with dramatic delivery.
Text to AudioEleven Multilingual V2
Most stable TTS model for professional content.
Text to AudioEleven Flash V2.5
Fastest TTS model with ultra-low latency.
Text to AudioEleven Turbo V2.5
Balanced TTS model with quality and speed.
Text to AudioEleven Flash V2
Ultra-fast English-only TTS model.
Text to AudioEleven Turbo V2
High-quality English TTS with low latency.
Audio to AudioElevenLabs Voice Changer
Transform voice recordings into different voices.
ElevenLabs Dubbing
AI-powered video/audio dubbing to translate content into 29+ languages.
WAN 2.2 Animate
Animate characters or replace them in videos using motion transfer.
Kling 2.6 Pro Motion Control
Transfer motion from reference videos to character images.
Kling O1 Video Edit
Edit videos with natural language instructions.
Lucy Edit Dev
Fast AI video editing with text prompts.
Lucy Edit Pro
Professional AI video editing with resolution control.
Lucy Restyle
AI video style transfer with motion preservation.
Kling Video O1
Generate videos from character/scene reference images.
Kling Video O1 Standard
Cost-effective reference-to-video generation.
WAN 2.6 Reference-to-Video
Transform video references into new video shots.
Speech to TextOpenAI Whisper
Fast, accurate multilingual speech-to-text.
Speech to TextOpenAI Whisper with Video
Transcribe video audio with timestamps.
Speech to TextOpenAI Whisper Turbo
Fastest Whisper model with great accuracy.
Text to 3DHunyuan3D v3
Generate detailed 3D models from text descriptions with texture support.
Image to 3DHunyuan3D v3 Image
Convert images to detailed 3D models with optional multi-view enhancement.
Image to 3DHunyuan3D v2.1
Single image to 3D with PBR materials and high-fidelity textures.
Image to 3DHunyuan3D v2 Base
High-fidelity 3D from single image with 4K textures.
Image to 3DHunyuan3D v2 Mini
Fastest and most affordable image-to-3D model.
Image to 3DHunyuan3D v2 Multi-View
Best accuracy from 3 reference images.
GPT-4o
OpenAI flagship multimodal model.
GPT-4.1
Latest GPT-4 with improved coding and reasoning.
O3
Advanced reasoning model with chain-of-thought.
GPT-5
Most capable GPT model.
Claude Sonnet 4.6
Latest Sonnet with near-Opus performance.
Claude Sonnet 4
Latest balanced model for coding and analysis.
Claude 3.5 Haiku
Fastest Claude model, cost-efficient.
Gemini 2.5 Flash
Fast and efficient with reasoning.
Gemini 2.0 Flash
Budget-friendly general purpose model.
Gemini 2.5 Flash Lite
Most affordable Gemini model.
Gemini 2.5 Pro
Premium Gemini with top-tier reasoning.
Gemini 3 Flash Preview
Next-gen Flash model preview.
DeepSeek R1
Reasoning model with chain-of-thought.
DeepSeek Chat
Fast and affordable general-purpose model.
GLM-5
Z.ai flagship model with advanced reasoning.
GLM-4.6V
Multimodal model with vision support.
Kimi K2.5
MoE model with 1T parameters.