Replicate has joined Cloudflare

Explore

Latest
black-forest-labs/flux-2-pro

FLUX.2 [pro]

Black Forest Labs' most advanced image generation model yet.

FLUX.2 [pro] delivers realistic high-resolution images with consistent multi-reference editing, precise control, character consistency, and context-aware creativity.

Get started
Blog posts
View more
Popular models
p-image-edit
prunaai

prunaai / p-image-edit

A sub 1 second 0.01$ multi-image editing model built for production use cases. For image generation, check out p-image here: https://replicate.com/prunaai/p-image

18M runs

Official
clip-features
andreasjansson

andreasjansson / clip-features

Return CLIP features for the clip-vit-large-patch14 model

142.6M runs

p-image
prunaai

prunaai / p-image

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

5.4M runs

Official
z-image-turbo
prunaai

prunaai / z-image-turbo

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

33.9M runs

Official
Not sure where to start?Learn more about Replicate

Official models

Official models are always on, maintained, and have predictable pricing.

View all official models

lightricks / ltx-2.3-pro

High-fidelity video generation with portrait support, audio-to-video, retake, and extend. Text, image, and audio-driven creation up to 4K at 50 FPS.

511 runs
Official
gpt-5.4

openai / gpt-5.4

OpenAI's most capable frontier model for complex professional work, coding, and multi-step reasoning.

456 runs
Official

lightricks / ltx-2.3-fast

Lightning-fast video generation with portrait support, camera controls, and synchronized audio. Up to 20 seconds at 1080p, 4K at 50 FPS.

934 runs
Official

kwaivgi / kling-v3-motion-control

Kling 3.0 motion control: transfer motion from a reference video to any character image with improved consistency and quality.

1.5K runs
Official
qwen-image-2-pro

qwen / qwen-image-2-pro

The pro version of Qwen Image 2 from Alibaba's Qwen team. Enhanced text rendering, realism, and semantic adherence for high-quality image generation and editing.

943 runs
Official
qwen-image-2

qwen / qwen-image-2

A next-generation image generation and editing model from Alibaba's Qwen team. Supports text-to-image and image editing with strong text rendering, especially for Chinese.

721 runs
Official

heygen / avatar-iv

Create realistic talking avatar videos from text with HeyGen's Avatar IV engine

31 runs
Official
music-2.5

minimax / music-2.5

Generate full-length songs with vocals, lyrics, and rich instrumentation from a text prompt

273 runs
Official

heygen / video-agent

Turn a text prompt into a complete, polished video with AI-generated script, avatar presenter, voiceover, visuals, and editing.

94 runs
Official
seedream-5-lite

bytedance / seedream-5-lite

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

64.2K runs
Official
gemini-3.1-pro

google / gemini-3.1-pro

Google's most intelligent model, with improved reasoning and a new medium thinking level

37.8K runs
Official

runwayml / gen-4.5

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

20K runs
Official
recraft-v4-pro-svg

recraft-ai / recraft-v4-pro-svg

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.

1.7K runs
Official
recraft-v4-svg

recraft-ai / recraft-v4-svg

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.

4.1K runs
Official
recraft-v4-pro

recraft-ai / recraft-v4-pro

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.

3.5K runs
Official
recraft-v4

recraft-ai / recraft-v4

Recraft's latest image generation model, built around design taste. Strong prompt accuracy, art-directed composition, and integrated text rendering. Fast and cost-efficient at standard resolution.

17.6K runs
Official

kwaivgi / kling-v3-video

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

38.2K runs
Official

kwaivgi / kling-v3-omni-video

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

28.5K runs
Official

kwaivgi / kling-o1

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

3.7K runs
Official
grok-imagine-image

xai / grok-imagine-image

SOTA image model from xAI

43K runs
Official

I want to…

View all collections

OCR to extract text from images

Use AI For Optical Character Recognition (OCR) to extract text from images via API

Classify text

Classify text by sentiment, topic, intent, or safety

Create realistic face swaps

Replace faces across images with natural-looking results.

Large Language Models (LLMs)

Explore Large Language Models (LLMs) for chat, generation & NLP tasks via API

Try AI models for free

Try AI Models for free: video generation, image generation, upscaling, and photo restoration

Vision models

Chat with images for understanding, captioning & detection via API

Object detection and segmentation

Use AI object detection and segmentation models to distinguish objects in images & videos

Official AI models

Official AI models: Always available, stable, and predictably priced

Flux fine-tunes

Flux fine-tunes: build and run custom AI image models via API

Media utilities

AI media utilities: auto-caption, watermark, frame extraction & more via API

Qwen-Image fine-tunes

Browse the diverse range of qwen-image fine-tunes the community has custom-trained on Replicate.

WAN family of models

WAN family of models: powerful image-to-video & text-to-video models

Latest models