生成和编辑图像，用你选择的模型。

Lightweight Seedream variant for fast, high-quality image generation.

ByteDance's flagship Seedream 5 model — top-tier aesthetic quality, prompt fidelity, and multi-reference editing up to 2K.

ByteDance's fast, low-cost Seedream 5 tier for high-volume image generation and editing, with multi-reference input.

ByteDance's versatile image model with strong aesthetic quality and prompt fidelity.

High-quality diffusion model for detailed, prompt-faithful image generation.

Alibaba's professional-grade Wan 2.7 image model for higher-fidelity, prompt-faithful generation and editing.

Google's updated Nano Banana 2 image model, with sharper graphic composition, steadier subjects across edits and closer prompt following, from text or up to 14 reference images at 1K to 4K.

Ultra-fast image generation model optimised for speed and creative output.

Google's fastest, most cost-efficient Nano Banana model — 1K images in ~4 seconds for high-volume workflows.

Google's Gemini 3 Pro image model, built for accurate text rendering, multi-image blending and studio-grade composition at up to 4K.

Professional-grade Flux model for photorealistic and artistic image synthesis.

Black Forest Labs' top-tier Flux 2 model — highest fidelity, strongest prompt adherence, and most stable multi-reference editing.

Black Forest Labs' image model on the FLUX 3 backbone: text-to-image, precise local edits, up to ten references, accurate typography, and native 4K output.

Black Forest Labs' smaller, faster FLUX 3 image model with open weights: text-to-image, image editing and multi-reference generation, with native 4K output.

Krea's fast image model for editing with plain-language instructions and up to eight input images; it also generates images from text at 1K or 2K.

OpenAI's state-of-the-art image generation model with precise instruction-following for both text-to-image and image editing.

OpenAI's detail-focused image model for dense compositions, text-heavy layouts and edits that stay consistent, with adjustable planning complexity, SVG output and animated GIF output.

OpenAI's fast image model for everyday generation and editing, about 50% faster than GPT Image 2.5, with adjustable planning complexity, SVG output and animated GIF output.

Meta Superintelligence Labs' agentic image model, which plans a layout and calls search and coding tools before it renders, for prompt-faithful generation, multi-reference composition and precise local edits.

Alibaba Qwen's hosted Pro tier of the Qwen Image 2.1 family, a unified model that generates from a prompt and edits or composes from up to 10 reference images. It can rewrite the prompt with an LLM before generating, with an optional thinking mode, and renders from 0.26 to 4.19 megapixels.

Alibaba Qwen's hosted Turbo tier of the Qwen Image 2.1 family, an 8-step checkpoint that generates from a prompt and edits or composes from up to 10 reference images at a low flat price. It can rewrite the prompt with an LLM before generating.

Microsoft AI's precision image model for design-ready visuals, which generates from a prompt and edits or composes from up to five reference images.

The lower-latency, lower-cost member of Microsoft AI's MAI-Image 2.6 family, built for high-throughput image generation and editing from up to five reference images.

The highest-fidelity tier of Microsoft AI's MAI-Image 2.5 family, producing photorealistic and artistic images from a prompt or one reference image.

Microsoft AI's image model for photorealistic and artistic images from a prompt or one reference image, in seven aspect ratios.

Alibaba Qwen's unified image generation and editing model, balancing visual quality, layout fidelity, and speed.

Alibaba Qwen's professional-grade image model for dense layouts, small-text rendering, and multilingual visual design.

Runway's Gen-4 image model with strong prompt adherence and tag-based reference images for consistent characters, styles, and scenes.

xAI's Grok image model for generation and editing, with quality-aware output control at up to 2K.

Recraft's design-focused image model, built around brand-consistent typography, layout, and colour control.

Recraft's premium design tier, for higher-resolution print-ready marketing and packaging visuals.

Ideogram's image model for precise generation and editing, with accurate typography, up to five reference images and masked edits.

Ideogram's first vector model: clean, editable SVG artwork with smooth gradients and sharp typography from a prompt, optionally guided by reference images.

Ideogram Vector 1.0's image-to-SVG mode: traces an attached JPEG, PNG or WebP into a scalable, editable vector, with no prompt.

Ideogram 3.0's character model: puts the character from one reference picture into new scenes and styles while keeping their face and look consistent.

Lifts the text out of a flat design: returns the design without its text plus each text block's words, position, font, size and colour, saved as one SVG with live, editable text.

Erases what a mask marks from a photo or design and fills the gap to match its surroundings, with no prompt.

Recraft's vector model, generating clean scalable SVG artwork with editable paths for logos, icons, and illustration.

Recraft's premium vector tier, producing higher-fidelity SVG artwork for branding and production layout work.

Pruna AI's fast, low-cost text-to-image model, built for production graphics at about half a cent an image.

Pruna AI's image upscaler, enlarging an attached image 2x to 16x (up to 8x on Replicate) with optional detail and realism enhancement. It takes no prompt.

Runway's fastest Gen-4 image model: generates from one to three tagged reference images for consistent characters, styles, and scenes at a fraction of Gen-4 Image's cost.

Kuaishou's Kling Image 3.0 model for consistent text-to-image and single-reference image editing at 1K or 2K.

Kuaishou's multi-reference Kling Image 3.0 Omni model with native 2K and 4K output from text and up to ten reference images.

High-speed image generation model optimised for low-latency creative output.

Compact 4B Flux diffusion model for fast, high-quality image generation.

Alibaba Qwen's 20B image model, running fully offline on your own machine. Known for rendering long passages of text — English and Chinese — inside the image, and needs no API key or network once the weights are downloaded.

Sperid Labs' 3B image model, running fully offline on your own machine. It generates directly in pixel space with no VAE, and needs no API key or network once the weights are downloaded.

Black Forest Labs' open-weight FLUX 3 image model, running fully offline on your own machine. It generates from a prompt in 16 steps and edits images you attach.

OpenMOSS's open 5B text-to-image model, running fully offline on your own machine. Qwen3.5 9B reads the prompt and the FLUX.2 VAE decodes the image, in 50 steps at CFG 3.