Replicate API：132 个工具，按次付费

Generate up to four images quickly from a text prompt with the official FLUX Schnell model.

Generate or edit one image with Gemini 3 Pro Image (Nano Banana Pro) at 1K, 2K or 4K through Replicate's official model.

Generate or edit images with GPT Image 2 through Replicate's official model, priced per image by quality.

Generate or edit images with GPT Image 2.5 Flare through Replicate's official model, priced per image by quality.

Generate or edit images with GPT Image 2.5 Sunburst through Replicate's official model, priced per image by quality.

FLUX1.1 [pro] in ultra and raw modes. Images are up to 4 megapixels. Use raw mode for realism.

Max-quality image generation and editing with support for ten reference images

Very fast image generation and editing model. 4 steps distilled, sub-second inference for production and near real-time applications.

The highest fidelity image model from Black Forest Labs

High-quality image generation and editing with support for eight reference images

A 12 billion parameter rectified flow transformer capable of generating images from text descriptions

A version of flux-dev, a text to image model, that supports fast fine-tuned lora inference

A premium text-based image editing model that delivers maximum performance and improved typography generation for transforming images through natural language prompts

A state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming images through natural language

State-of-the-art image generation with top of the line prompt following, visual quality, image detail and output diversity.

SOTA Open source model trained on licensed data, transforming intent into structured control for precise, high-quality AI image generation in enterprise and agentic workflows.

Commercial-ready, trained entirely on licensed data, text-to-image model. With only 4B parameters provides exceptional aesthetics and text rendering. Evaluated to be on par to other leading models in the market

A text-to-image model with support for native high-resolution (2K) image generation

Unified text-to-image generation and precise single-sentence editing at up to 4K resolution

Seedream 4.5: Upgraded Bytedance image model with stronger spatial understanding and world knowledge

Seedream 5.0 lite: image generation with built-in reasoning, example-based editing, and deep domain knowledge

Google's highest quality text-to-image model, capable of generating images with detail, rich lighting and beauty

A faster and cheaper Imagen 3 model, for when price or speed are more important than final image quality

Google's Imagen 4 flagship model

Use this fast version of Imagen 4 when speed and cost are more important than quality

Use this ultra version of Imagen 4 when quality matters more than speed and cost

Google's latest image editing model in Gemini 2.5

Google's fast image generation model with conversational editing, multi-image fusion, and character consistency

An excellent image model with state of the art inpainting, prompt comprehension and text rendering

A fast image model with state of the art inpainting, prompt comprehension and text rendering.

Like Ideogram v2, but faster and cheaper

Like Ideogram v2 turbo, but now faster and cheaper

Balance speed, quality and cost. Ideogram v3 creates images with stunning realism, creative designs, and consistent styles

The highest quality Ideogram v3 model. v3 creates images with stunning realism, creative designs, and consistent styles

Turbo is the fastest and cheapest Ideogram v3. v3 creates images with stunning realism, creative designs, and consistent styles

Artistic and high-quality visuals with improved prompt adherence, diversity, and definition

High-quality image generation model optimized for creative professional workflows and ultra-high fidelity outputs

Accelerated variant of Photon prioritizing speed while maintaining quality

Minimax's first image model, with character reference support

OpenAI's latest image generation model with better instruction following and adherence to prompts

This is the fastest Flux endpoint in the world.

This is an optimised version of the hidream-l1 model using the pruna ai optimisation toolkit!

A sub 1 second text-to-image model built for production use cases.

Use trained LoRAs from the https://replicate.com/prunaai/p-image-trainer. Find or contribute LoRAs here https://huggingface.co/collections/PrunaAI/p-image-loras

This model generates beautiful cinematic 2 megapixel images in 3-4 seconds and is derived from the Wan 2.2 model through optimisation techniques from the pruna package

Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.

Generate editable SVG graphics from text prompts with Quiver's Arrow 1.1 model. Great for icons, logos, and illustrations.

Generate high-fidelity SVG graphics from text prompts with Quiver's Arrow 1.1 Max model. Tuned for dense illustrations, detailed logos, and technical diagrams.

An image generation foundation model in the Qwen series that achieves significant advances in complex text rendering.

Recraft V3 (code-named red_panda) is a text-to-image model with the ability to generate long texts, and images in a wide list of styles. As of today, it is SOTA in image generation, proven by the Text-to-Image Benchmark by Artificial Analysis

Recraft V3 SVG (code-named red_panda) is a text-to-image model with the ability to generate high quality SVG images including logotypes, and icons. The model supports a wide list of styles.

Recraft's latest image generation model at ~2048px resolution. Same design taste and prompt accuracy as V4, with higher resolution for print-ready and large-scale work.

Generate detailed SVG vector graphics from text prompts. Recraft V4 Pro's design taste with more geometric detail and finer paths - clean layers, editable output, and scalable to any size.

Recraft V4 Styles Pro SVG generates high-quality editable vector images that match a reusable style or attached reference images.

Generate production-ready SVG vector images from text prompts. Recraft V4's design taste applied to vector output - clean geometry, structured layers, and editable paths.

Agentic image model optimized for robust, high-precision generations supporting font control

A text-to-image model that generates high-resolution images with fine details. It supports various artistic styles and produces diverse outputs from the same prompt, thanks to Query-Key Normalization.

A text-to-image model that generates high-resolution images with fine details. It supports various artistic styles and produces diverse outputs from the same prompt, with a focus on fewer inference steps

2.5 billion parameter image model with improved MMDiT-X architecture

A powerful native multimodal model for image generation (PrunaAI squeezed)

Generate and edit images with Alibaba's Wan 2.7

Generate and edit high-quality images with Alibaba's Wan 2.7 Pro with 4K output, thinking mode, text-to-image, multi-image editing, and image set generation

SOTA image model from xAI

Read a prediction's status; a succeeded prediction carries its output URL(s) in `output`. Copy outputs promptly: Replicate removes prediction data after a retention window.

Generate a 480P, 720P, or 1080P video from text or a starting image.

Generate a short video from text or an image, with optional synchronized audio.

Alibaba's Happy Horse 1.0 generates videos from text prompts or animates a single image into video. Supports 720p and 1080p, 3-15 second durations, and five aspect ratios.

Alibaba's Happy Horse 1.1 generates videos from text, animates a single image, or builds a video from multiple reference images. Supports 720p and 1080p, 3-15 second durations, and five aspect ratios.

(50% off until Aug 30!) - Wan 3.0 generates video from a text prompt or a starting image, with cinematic motion and support for 480p, 720p, and 1080p output up to 30 seconds.

Animate any character, humans, cartoons, animals, even non-humans, from a single image + driving video

A joint audio-video model that accurately follows complex instructions.

A pro version of Seedance that offers text-to-video and image-to-video support for 5s or 10s videos, at 480p and 1080p resolution

A faster and cheaper version of Seedance 1 Pro

ByteDance's multimodal video generation model with native audio, multimodal reference inputs, and intelligent duration control.

A faster variant of Seedance 2.0 for quicker video generation with multimodal inputs and native audio.

State of the art video generation model. Veo 2 can faithfully follow simple and complex instructions, and convincingly simulates real-world physics as well as a wide range of visual styles.

Sound on: Google’s flagship Veo 3 text to video model, with audio

New and improved version of Veo 3, with higher-fidelity video, context-aware audio, reference image and last frame support

A faster and cheaper version of Google’s Veo 3 video model, with audio

Modify an existing video through natural-language commands, changing subjects, environments, and visual style while preserving the original motion and timing.

Generate 5s and 10s videos in 1080p resolution

Generate 5s and 10s videos in 720p resolution at 30fps

Generate 5s and 10s videos in 720p resolution

Use Kling v2.1 to generate 5s and 10s videos in 720p and 1080p resolution from a starting image (image-to-video)

A premium version of Kling v2.1 with superb dynamics and prompt adherence. Generate 1080p 5s and 10s videos from text or an image

Kling 2.5 Turbo Pro: Unlock pro-level text-to-video and image-to-video creation with smooth motion, cinematic depth, and remarkable prompt adherence.

Kling 2.6 Pro: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation

Kling Video 3.0 Omni: Unified multimodal video generation with reference images, video editing, native audio, and multi-shot control

Kling Video 3.0: Generate cinematic videos up to 15 seconds with multi-shot control, native audio, and improved consistency

Create 5s 480p videos from a text prompt

Modify a video with style transfer and prompt-based editing

Generate 5s and 9s 540p videos

Generate 5s and 9s 720p videos

Luma's reasoning video model. Generates cinematic 5s or 10s video from text or images, with native HDR and EXR export for professional production pipelines.

Generate 5s and 9s 540p videos, faster and cheaper than Ray 2

Generate 5s and 9s 720p videos, faster and cheaper than Ray 2

Hailuo 2 is a text-to-video and image-to-video model that can make 6s or 10s videos at 768p (standard) or 1080p (pro). It excels at real world physics.

A high-fidelity video generation model optimized for realistic human motion, cinematic VFX, expressive characters, and strong prompt and style adherence across both text-to-video and image-to-video workflows

A lower-latency image-to-video version of Hailuo 2.3 that preserves core motion quality, visual consistency, and stylization performance while enabling faster iteration cycles.

Generate 6s videos with prompts or images. (Also known as Hailuo). Use a subject reference to make a video with a character and the S2V-01 model.

Generate videos with specific camera movements

An image-to-video (I2V) model specifically trained for Live2D and general animation use cases

OpenAI's Flagship video generation with synced audio

OpenAI's Most advanced synced-audio video generation

Quickly generate smooth 5s or 8s videos at 540p, 720p or 1080p

Quickly make 5s or 8s videos at 540p, 720p or 1080p. It has enhanced motion, prompt coherence and handles complex actions well.

Create 5s-8s videos with enhanced character movement, visual effects, and exclusive 1080p-8s support. Optimized for anime characters and complex actions

Latest video model from Pixverse with astonishing physics

PixVerse's flagship video generation model. Generate cinematic videos with synchronized audio, multi-shot sequences, and precise camera control.

Fast video generation with built-in draft mode for rapid creative iteration. Text-to-video, image-to-video, and audio-to-video in a single endpoint.

p-video-animate animates a reference image with the motion and audio of a source video. Optimized for speed and cost - 5.24s per 1s of video.

p-video-avatar is the fastest and cheapest avatar/lipsync video model on the market.

State-of-the-art video motion quality, prompt adherence and visual fidelity

VEED Fabric 1.0 is an image-to-video API that turns any image into a talking video

High-fidelity video generation with text-to-video, image-to-video, and start-end-to-video modes. Up to 16 seconds at 1080p with synchronized audio.

Generate 5s 480p videos. Wan is an advanced and powerful visual generation model developed by Tongyi Lab of Alibaba Group

Image-to-video at 720p and 480p with Wan 2.2 A14B

A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B image-to-video

A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B text-to-video

Alibaba Wan 2.5 Image to video generation with background audio

Wan 2.5 image-to-video, optimized for speed

Alibaba Wan 2.5 text to video generation model

Wan 2.5 text-to-video, optimized for speed

Generate videos from images, with support for first-and-last-frame control, clip continuation, and audio synchronization using Alibaba's Wan 2.7 model

Generate videos from reference images or clips while preserving subject identity using Alibaba's Wan 2.7 reference-to-video model

Accelerated inference for HunyuanVideo with high resolution (1280x720), a state-of-the-art text-to-video generation model capable of creating high-quality videos with realistic motion from text descriptions

Accelerated inference for Wan 2.1 14B image to video, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.

Accelerated inference for Wan 2.1 14B image to video with high resolution, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.

Accelerated inference for Wan 2.1 14B text to video, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.

Accelerated inference for Wan 2.1 14B text to video with high resolution, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.

Generate videos using xAI's Grok Imagine Video model

Image-to-video with synchronized audio using xAI's Grok Imagine Video 1.5 preview model