热门AI视频Kling 3.0 Omni
Kling 3.0 Omni text, image, reference, and transformation video.
1080pReferenceKling
探索模型
挑选视频、图片或音频模型，然后回到生成器继续创作。
80 个模型
- 热门AI视频
- 热门AI视频
Kling 3.0
Multi-shot Kling 3.0 video with element references and motion control.
1080p5-15sKling 
热门AI视频Veo 3.1
Google DeepMind Veo 3.1 with native 1080p, audio, and 4K upscale.
1080p4KAudioGoogle
热门AI图片Imagen 4 Ultra
Google Imagen 4 Ultra for highest-fidelity photorealistic stills.
GooglePhotoreal
热门AI图片Nano Banana Pro
Sharper 2K imagery, 4K scaling, and stronger character consistency.
2K4KGoogle
热门AI图片GPT Image 2
OpenAI next-gen stills with photorealism, text rendering, and references.
OpenAIReference
热门AI声音Suno
Text-to-music with vocals or instrumentals; KIE supports the latest V5.5.
MusicV5.5Lyrics
新的AI视频Seedance 2.5
Up to 30s cinematic video with multimodal image, video, and audio references.
Audio720p4-30sByteDance- 新的AI视频
Seedance 2.0 Fast
Faster Seedance 2.0 for quicker cinematic drafts.
FastByteDance 
新的AI视频Hailuo 2.3 Pro
MiniMax Hailuo 2.3 Pro image-to-video.
2KMiniMax
新的AI视频MiniMax H3
MiniMax H3 text, image, and reference-to-video generation.
MiniMaxReference
新的AI视频Wan 2.7
Wan 2.7 text, image, reference-to-video, and video edit.
1080pWan
新的AI视频Grok Imagine 1.5
xAI video 1.5 with synced audio and stronger prompt adherence.
xAIAudio
新的AI视频HappyHorse 1.1
HappyHorse 1.1 text, image, and reference-to-video.
Reference- 新的AI视频
Gemini Omni Video
Gemini Omni video generation from prompts and images.
GoogleOmni - 新的AI视频
OmniHuman 1.5
OmniHuman 1.5 human video with subject detection helpers.
HumanAudio - 新的AI图片
Seedream 5.0 Pro
ByteDance multimodal image model for controlled generation, portraits, and precise edits.
2KImage to imageByteDance - 新的AI图片
Nano Banana 2
Gemini 3.1 Flash Image: fast generation, text rendering, and character consistency.
GoogleStyleImage to image 
新的AI图片Flux 2 Pro
Detail-rich Flux 2 Pro stills for product, portrait, and brand work.
2KImage to image- 新的AI图片
Grok Imagine Image 2.0
xAI image 2.0 with text-to-image, edit, and segment-map workflows.
xAIEdit - 新的AI图片
Qwen3 Pro
Qwen3 Pro photoreal stills with text-to-image and image-to-image.
QwenImage to image - 新的AI图片
Wan 2.7 Image Pro
Wan 2.7 Pro image generation and editing.
WanEdit 
新的AI声音ElevenLabs Turbo 2.5
Fast ElevenLabs text-to-speech (Turbo 2.5).
TTSFast- 新的AI声音
Gemini 3.1 Flash TTS
Gemini 3.1 Flash text-to-speech.
TTSGoogle - AI视频
Seedance 2.0
ByteDance multimodal video with strong multi-shot consistency.
720p4-15sByteDance - AI视频
Seedance 2.0 Mini
Compact Seedance 2.0 variant for lighter video jobs.
FastByteDance - AI视频
Seedance 1.5 Pro
Seedance 1.5 Pro cinematic video generation.
ByteDancePro - AI视频
ByteDance V1 Pro
ByteDance V1 Pro text-to-video and image-to-video.
ByteDanceImage to video - AI视频
ByteDance V1 Lite
ByteDance V1 Lite for faster text and image to video.
FastByteDance - AI视频
Kling 3 Turbo
Faster Kling 3 text-to-video and image-to-video.
FastKling - AI视频
Kling 2.6
Kling 2.6 text-to-video, image-to-video, and motion control.
KlingMotion - AI视频
Kling 2.5 Turbo Pro
Kling 2.5 Turbo Pro text and image to video.
FastProKling - AI视频
Kling 2.1 Master
Kling 2.1 Master text-to-video and image-to-video.
MasterKling - AI视频
Kling 2.1 Pro
Kling 2.1 Pro video generation.
ProKling - AI视频
Kling 2.1 Standard
Kling 2.1 Standard video generation.
Kling - AI视频
Kling AI Avatar Pro
Talking-avatar video with Kling AI Avatar Pro.
AvatarAudio - AI视频
Kling AI Avatar
Standard Kling talking-avatar generation.
AvatarAudio - AI视频
Hailuo 2.3
MiniMax Hailuo 2.3 Standard image-to-video.
MiniMaxImage to video - AI视频
Hailuo 02 Pro
Hailuo 02 Pro text-to-video and image-to-video.
ProMiniMax - AI视频
Hailuo 02
Hailuo 02 Standard text-to-video and image-to-video.
MiniMax - AI视频
Wan 2.6
Wan 2.6 text, image, and video-to-video generation.
WanVideo to video - AI视频
Wan 2.6 Flash
Faster Wan 2.6 flash image and video-to-video.
FastWan - AI视频
Wan 2.5
Wan 2.5 text-to-video and image-to-video.
Wan - AI视频
Wan 2.2 Turbo
Wan 2.2 A14B turbo text, image, and speech-to-video.
FastSpeechWan - AI视频
Wan Animate
Wan animate move and character-replace video.
AnimateWan - AI视频
Grok Imagine Video
xAI Grok Imagine text/image-to-video with upscale and extend.
xAIExtend 
AI视频PixVerse V6
PixVerse V6 text, image, transition, extend, and reference video.
ExtendReference- AI视频
HappyHorse
HappyHorse text, image, reference-to-video, and video edit.
EditReference 
AI视频Runway Gen-4
Runway text/image-to-video, extend, and Aleph video-to-video.
RunwayExtend
AI视频Topaz Video Upscale
Topaz AI video upscaling for resolution and quality.
Upscale- AI视频
Infinitalk
Talking-head video from audio with Infinitalk.
AvatarAudio 
AI视频Volcengine Lip Sync
Video-to-video lip sync from Volcengine.
Lip syncAudio- AI图片
Seedream 5.0 Lite
Faster Seedream 5.0 image generation and editing for iteration-heavy workflows.
FastImage to image - AI图片
Seedream 4.5
Photorealistic image generation and editing from Seedream 4.5.
PhotorealImage to image - AI图片
Seedream 4.0
High-quality photorealistic images with Seedream 4.0 text and edit modes.
PhotorealEdit - AI图片
Seedream 3.0
Seedream 3.0 text-to-image for portraits, products, and scenes.
Text to image 
AI图片Z-Image
General-purpose image generation via the Z-Image model.
Text to image- AI图片
Imagen 4
Google Imagen 4 text-to-image with strong prompt adherence.
GoogleText to image - AI图片
Imagen 4 Fast
Faster Imagen 4 generation for drafts and layout tests.
GoogleFast - AI图片
Nano Banana 2 Lite
Lighter Nano Banana 2 variant for quicker image generation.
GoogleFast - AI图片
Nano Banana
Stylized image generation and Nano Banana edit workflows.
StyleEdit - AI图片
Flux 2 Flex
Flexible Flux 2 generation for fast layout and style tests.
FastImage to image - AI图片
Flux Kontext
Flux Kontext generate-or-edit for prompt-driven image revisions.
EditImage to image - AI图片
Grok Imagine Image
xAI Grok Imagine stills from text or reference images.
xAIImage to image - AI图片
GPT Image 1.5
GPT Image 1.5 text-to-image and image-to-image generation.
OpenAIImage to image - AI图片
GPT-4o Image
4o image generation tasks with 14-day result retention.
OpenAIText to image - AI图片
Qwen3
Qwen3 image generation and image-to-image editing.
QwenImage to image - AI图片
Qwen2
Qwen2 text-to-image and image-edit endpoints.
QwenEdit - AI图片
Qwen
Qwen photoreal generation plus image-to-image and edit.
QwenPhotoreal 
AI图片Ideogram V3
Ideogram V3 stills with strong typography, plus edit and remix.
TextEditRemix- AI图片
Ideogram Character
Consistent character generation with edit and remix variants.
CharacterEdit - AI图片
Wan 2.7 Image
Wan 2.7 image generation and editing.
WanEdit - AI图片
Topaz Image Upscale
Topaz AI upscaling to raise resolution and detail.
Upscale 
AI图片Recraft Upscale
Recraft crisp upscale for sharper brand-ready stills.
UpscaleBrand- AI图片
Recraft Remove BG
Remove image backgrounds with Recraft.
BackgroundEdit - AI声音
ElevenLabs Multilingual
ElevenLabs multilingual v2 text-to-speech.
TTSMultilingual - AI声音
ElevenLabs Dialogue V3
Multi-speaker dialogue generation with ElevenLabs V3.
TTSDialogue - AI声音
ElevenLabs Isolation
Isolate vocals or stems from mixed audio.
StemsCleanup - AI声音
Gemini 2.5 Pro TTS
Gemini 2.5 Pro text-to-speech.
TTSGoogle - AI声音
Gemini Omni Audio
Gemini Omni audio generation from text or references.
AudioGoogle