一站式 AI 中心
欢迎使用你的 AI 工具中心。这里汇聚了我们全部的智能能力——从强大的大语言模型（LLM）到前沿的图像与视频生成模型，专为顺畅浏览与快速接入而打造。一眼即可对比并选用最适合你工作流的引擎。
Qwen Image 3.0 Text-to-Image
Generates images from a text prompt at resolutions up to 2048×2048, with automatic prompt rewriting and prompt-guided resolution selection, building on Qwen strength in complex text rendering and precise prompt adherence
Qwen Image 3.0 Edit
Edits images from one to three reference images and a natural-language instruction, preserving key details such as facial features and identity while applying the requested changes
Qwen3.8 Max
Next-generation flagship model for advanced reasoning, coding, and multimodal AI applications.
MiniMax H3 Text-to-Video
MiniMax H3 text-to-video: generate a cinematic video from a text prompt. Supports 2K, 5-15s., and 16:9/9:16/1:1/adaptive aspect ratios.
MiniMax H3 Image-to-Video
MiniMax H3 image-to-video: animate a first-frame image (optionally with a last frame) driven by a text prompt. Supports 2K, 5-15s.
MiniMax H3 Reference-to-Video
MiniMax H3 reference-to-video: generate a video that keeps the subject from a reference image, driven by a text prompt. Supports 2K, 5-15s.
Reve 2.1 Remix
Reve 2.1 Remix composes one to six reference images with a natural-language prompt into a single coherent image at native 4K, blending subject, style, and background while keeping references consistent.
Reve 2.1 Edit
Reve 2.1 Edit applies precise, instruction-driven, element-level edits to a single input image at native 4K, changing targeted regions while preserving the rest of the scene.
Reve 2.1 Text-to-Image
Reve 2.1 is a layout-first text-to-image model that turns natural-language prompts into sharp, production-ready images at native 4K, with best-in-class typography and high prompt adherence.
Kimi K3
Top-performing open-weight model optimized for frontier reasoning, coding, and enterprise AI applications.
Grok 4.5
Flagship conversational model built for real-time knowledge exploration, sharp reasoning, and highly engaging AI interactions.
Youchuan V8.2 Image-to-Video
Youchuan V8.2 animates an input image into four 5-second videos at 480p or 720p.
Youchuan V8.2 Remove Background
Youchuan automatically removes the background from an input image, returning one transparent-background result.
Youchuan V8.2 Style Transfer
Youchuan retexture changes the artistic style of an input image while preserving its composition, returning four restyled results.
Youchuan V8.2 Blend
Youchuan V8.2 blends two to five input images into four fused results, with an optional guiding prompt and native 2K HD.
Youchuan V8.2 Image-to-Image
Youchuan V8.2 re-imagines an input image guided by a text prompt, returning four variations. Supports native 2K HD, style reference, and aspect-ratio / stylize / chaos / weird controls.
Youchuan V8.2 Text-to-Image
Youchuan V8.2 generates four images from a text prompt, with optional native 2K HD, a style reference, and aspect-ratio / stylize / chaos / weird controls.
Wan 2.7 Spicy Reference-to-Video
An image-reference-to-video model that generates one continuous video from one to four reference images with precise subject binding and prompt control. Supports image references only; reference video and audio are not accepted.
Wan 2.7 Spicy Image-to-Video
AtlasCloud Wan 2.7 Spicy Image-to-Video turns a first-frame image into short cinematic motion with stable temporal detail and expressive character movement.
Seedream v5.0 Pro Edit
ByteDance flagship next-generation image editing model. Supports up to 10 reference images while preserving identity, lighting, and color tones for professional-quality modifications.
Seedream v5.0 Pro Text-to-Image
ByteDance flagship next-generation image generation model with stronger prompt adherence, refined typography, and photorealistic detail. Single-image output at 1.5K and 2K tiers with JPEG and PNG support.
KAT Coder Pro V2.5
High-end coding agent built for complex software engineering, repository-scale tasks, and autonomous development workflows.
KAT Coder Air V2.5
Fast, lightweight coding model designed for interactive development, rapid code iteration, and efficient coding agents.
Nano Banana 2 Lite Edit Developer
Google's fastest and most cost-efficient Nano Banana image model for editing, applying natural-language edits and multi-image composition to up to 14 reference images with low latency.
Nano Banana 2 Lite Text-to-Image Developer
Google's fastest and most cost-efficient Nano Banana image model, turning natural-language text prompts into high-quality 1k images in as little as 4 seconds for rapid, high-volume generation.
Nano Banana 2 Lite Edit
Nano banana lite is the efficiency-focused model in the image generation family. Sub-2 second latency with cost-effective generation and editing, fast multi-turn local edits, and 14 supported aspect ratios.
Nano Banana 2 Lite Text-to-image
Nano banana lite is the efficiency-focused model in the image generation family. Sub-2 second latency with cost-effective generation and editing, fast multi-turn local edits, and 14 supported aspect ratios.
Seed Audio 1.0
Doubao‑Audio‑Generate‑1.0 is Doubao Voice’s next‑generation audio‑generation engine. The industry‑first commercial tool creates film‑grade audio with just one prompt. It eliminates cumbersome audio‑engineering work. Creators generate publish‑ready radio dramas, podcasts and branded audio easily, shifting from a simple voice‑generator to an AI audio director. It serves audiobooks, serialized episodes and commercial audio for high‑quality narrative‑driven production.
Doubao Seed Character
Flagship model delivering premium reasoning, coding, multimodal understanding, and enterprise-grade performance.
Doubao Seed 2.1 Turbo
Turbo model optimized for ultra-low latency, high throughput, and responsive AI experiences.
Doubao Seed 2.1 Pro
Flagship model delivering premium reasoning, coding, multimodal understanding, and enterprise-grade performance.
Seedance 2.0 Mini Reference-to-Video
Lightweight, economical multimodal video generation from reference images, videos, and audio with native audio.
Seedance 2.0 Mini Image-to-Video
Lightweight, economical video generation from a first-frame image (and optional last-frame) with native audio.
Seedance 2.0 Mini Text-to-Video
Lightweight, economical video generation from text prompts with native audio.
HappyHorse-1.1 Text-to-video
Generates videos from text prompts with HappyHorse 1.1, supporting 720P or 1080P output, flexible aspect ratios, and durations from 3 to 15 seconds.
HappyHorse-1.1 Image-to-video
Animates a first-frame image into video with optional prompt guidance, 720P or 1080P output, and durations from 3 to 15 seconds.
HappyHorse-1.1 Reference-to-video
Generates videos from one to nine reference images and a text prompt, supporting 720P or 1080P output, flexible aspect ratios, and durations from 3 to 15 seconds.
GLM 5.2
Agent-oriented model built for complex reasoning, tool use, and autonomous task execution.
Gemini Omni Flash Reference-to-Video
A natively multimodal Google DeepMind model that generates cinematic, sound-enabled videos from a text prompt plus 1-5 reference images, carrying a consistent subject, scene, or style across generations.
Gemini Omni Flash Image-to-Video
A natively multimodal Google DeepMind model that animates a still image into a cinematic, sound-enabled video guided by a text prompt while preserving the source subject and composition.
Gemini Omni Flash Video Edit
A natively multimodal Google DeepMind model that edits an existing video from a text prompt with optional reference images, applying scene-consistent changes and native audio while preserving the untouched footage.
Gemini Omni Flash Text-to-Video
A natively multimodal Google DeepMind model that generates cinematic videos with synchronized native audio from a text prompt alone, grounded in real-world physics for controllable, high-speed video generation.
Kimi K2.7 Code
Powerful coding model for programming, debugging, and AI developer workflows.
Gemini Omni Flash Reference-to-Video Developer
Gemini Omni Flash is Google's multimodal video generation model. This reference-to-video variant transforms existing video clips using reference images and text prompts, enabling video style transfer, scene editing, and character insertion.
MiniMax M3
MiniMax M3 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world capability while maintaining exceptional latency, scalability, and cost efficiency.
Avatar Omni Human 1.5
OmniHuman 1.5 is ByteDance's digital-human model that turns a single portrait plus an audio track into a lifelike video of that character speaking or singing, with lip-sync, expressions, and gestures generated straight from the audio.
Kling V3.0 Turbo Image-to-Video
Kling V3.0 Turbo Image-to-Video transforms static images into dynamic cinematic videos using MVL technology. Supports first/last frame control and audio generation.
Kling V3.0 Turbo Text-to-Video
Kling V3.0 Turbo Text-to-Video generates dynamic cinematic videos from text prompts using MVL technology. Supports first/last frame control and audio generation.
