高级Generative 图片
google/nano-banana-2
Google 图片 generation with conversational editing, multi-image fusion and character consistency.
Open modelGenerative 图片
文本 and reference-image models for 高级 visual creation.
高级
高级Generative 图片
openai/gpt-image-2
OpenAI 图片 generation and editing with strong instruction following and sharp 文本 rendering.
Open model
高级Generative 图片
bytedance/seedream-4.5
Bytedance Seedream 4.5 图片 generation with stronger spatial understanding and world knowledge.
Open model
高级Generative 图片
xai/grok-imagine-image
xAI 图片 generation for expressive, high-detail creative scenes.
Open model
高级Generative 图片
google/imagen-4-fast
Fast Imagen 4 generation when speed and cost matter.
Open modelAnime style
Anime generation and anime-style 图片 transformation models.
Generate emojis
创建 custom emoji-style assets from short prompts.
Restore 图片
Restore old photos, damaged 图片 and faces with AI repair models.
3D content
创建 textured 3D assets and downloadable model 文件 from prompts or reference 图片.
Generative videos
Prompt-到-video and reference-video generation models.
高级Generative videos
xai/grok-imagine-video
Generate videos using xAI Grok Imagine 视频.
Open model
高级Generative videos
bytedance/seedance-1-lite
Seedance Lite text-到-video and image-到-video generation.
Open model
高级Generative videos
openai/sora-2-pro
OpenAI Sora 2 Pro synced-audio 视频 generation.
Open model
高级Generative videos
wan-video/wan-2.2-t2v-fast
A fast optimized Wan 2.2 text-到-video model.
Open model
高级Generative videos
alibaba/happyhorse-1.0
Alibaba Happy Horse turns prompts or a reference 图片 into cinematic HD 视频 clips with duration and aspect controls.
Open model
高级Generative videos
prunaai/p-video-avatar
创建 a talking avatar 视频 from one portrait 图片, a script, selected 语音 and language.
Open model
高级Versioned studio
okaris/roop
Swap a source face into a target 视频 clip with a dedicated 视频 face-swap workflow.
Open modelFace & 图片 editing
Face-aware 图片 editing, reference and identity-preserving 图片 models.
图片 upscalers
Super-resolution and crisp 图片 enhancement models.
音乐 generation
Full songs, instrumentals and 音频 generation models.
文本 到 speech
语音 synthesis and 语音 cloning models.
高级文本 到 speech
inworld/realtime-tts-2
Inworld realtime text-到-speech with preset voices.
Open model
高级文本 到 speech
minimax/speech-02-turbo
MiniMax low-latency multilingual text-到-audio with emotion control.
Open model
高级Versioned studio
jaaari/kokoro-82m
Kokoro 82M text-到-speech based on StyleTTS2.
Open model
高级Versioned studio
lucataco/xtts-v2
Coqui XTTS-v2 multilingual text-到-speech 语音 cloning.
Open model视频 captions
视频 understanding, transcript and caption generation models.
Large language models
聊天, coding, reasoning and multimodal language models.
高级Large language models
google/gemini-3.1-pro
Google Gemini 3.1 Pro for reasoning, research and high-quality 聊天.
Open model
高级Large language models
openai/gpt-5.2
OpenAI GPT-5.2 for coding, agentic work, reasoning and multimodal tasks.
Open model
高级Large language models
google/gemini-3-pro
Google Gemini 3 Pro advanced reasoning with multimodal input support.
Open model
高级Large language models
deepseek-ai/deepseek-v3.1
DeepSeek V3.1 hybrid thinking model for coding and technical work.
Open model
高级Large language models
qwen/qwen3-235b-a22b-instruct-2507
Qwen3 large instruction model for writing, planning and structured answers.
Open model