Skip to main content

Replicate

Access thousands of community AI models through Replicate.

A versatile node capable of interfacing with the Replicate API. Explore thousands of models for text, image, audio, and 3D generation. Replicate cost varies per model.

Replicate
ModelText
Dots are connection handles.

Settings

SettingTypeDefaultDescription
ModelTextReplicate model name with version (e.g. 'owner/model:version'). You can find the model name and version on the model's page on Replicate.

A curated selection — any model of the platform can be used from the node's model picker.

ModelWhat it does
Google Nano Banana 2Google's latest image editing model in Gemini 3.1
Google Nano Banana ProGoogle's latest image editing model in Gemini 3 Pro
Seedance 2.0A pro version of Seedance that offers text-to-video and image-to-video support for 5s or 10s videos, at 480p and 1080p resolution.
Seedance 2.0 FastA pro version of Seedance that offers text-to-video and image-to-video support for 5s or 10s videos, at 480p and 1080p resolution.
Seedance 2.0 MiniA pro version of Seedance that offers text-to-video and image-to-video support for 5s or 10s videos, at 480p and 1080p resolution.
Google Veo 3.1Google’s flagship Veo 3 text to video model, with audio
Google Veo 3.1 FastGoogle’s flagship Veo 3 text to video model, with audio
Kling v3 VideoKling delivers robust video generation and animation solutions, available in both professional and standard versions.
Kling v3 Omni VideoKling delivers robust video generation and animation solutions, available in both professional and standard versions.
Kling v3 Motion ControlKling delivers robust video generation and animation solutions, available in both professional and standard versions.
Seedream 4.5A text-to-image model with support for native high-resolution (2K) image generation
Seedream 5 ProByteDance's flagship image model for high-quality 1K and 2K generation from text or up to 10 reference images
FLUX 2 MaxHigh-quality image generation and editing with support for eight reference images
FLUX 2 ProHigh-quality image generation and editing with support for eight reference images
FLUX 2 Klein 9BHigh-quality image generation and editing with support for eight reference images
FLUX 2 Klein 4BHigh-quality image generation and editing with support for eight reference images
P Image EditpImageEditDescription
P ImagepImageDescription
P VideoFast video generation with Pruna's p-video model.
P Video AvatarFast talking avatar video generation with Pruna's p-video-avatar model.
Google Nano BananaGoogle's latest image editing model in Gemini 2.5
LTX 2 Distilledltx2Description
Seedance 1.5 ProA pro version of Seedance that offers text-to-video and image-to-video support for 5s or 10s videos, at 480p and 1080p resolution.
Qwen Image EditEdit images using a prompt. This model extends Qwen-Image’s unique text rendering capabilities to image editing tasks, enabling precise text editing.
FLUX Kontext ProA 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
Recraft V4Recraft V3 is a text-to-image model with the ability to generate long texts, and images in a wide list of styles.
Recraft V4 ProRecraft V3 is a text-to-image model with the ability to generate long texts, and images in a wide list of styles.
FLUX Kontext MaxA 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
BRIA Remove BackgroundRemove the background from an image using lucataco/remove-bg from Replicate API.
Recraft V4 SVGRecraft SVG offers advanced vector image generation, enabling scalable and creative SVG designs.
Recraft V4 Pro SVGRecraft SVG offers advanced vector image generation, enabling scalable and creative SVG designs.
Google UpscalerUpscale an image using Google's model.
Clarity Pro UpscalerclarityProUpscalerDescription
Upscale ImageReal-ESRGAN with optional face correction and adjustable upscale
Face SwapSeamlessly swap faces between images, allowing for realistic and precise facial replacements.
FLUX Fill ProGenerate an image using the FLUX model.
FLUX Kontext Dev LoraA version of flux-dev, a text to image model, that supports fast fine-tuned lora inference.
FLUX Dev LoraA version of flux-dev, a text to image model, that supports fast fine-tuned lora inference.
FLUX Dev Multi LoraA version of flux-dev, a text to image model, that supports fast fine-tuned lora inference.
Wan 2.6 T2VAn open suite of video foundation models.
Wan 2.6 I2VAn open suite of video foundation models.
Wan 2.2 T2V FastAn open suite of video foundation models.
Wan 2.2 I2V FastAn open suite of video foundation models.
Music-1.5Quickly generate up to 1 minute of music with lyrics and vocals in the style of a reference track
Speech-2.6 HDText-to-Audio (T2A) that offers voice synthesis, emotional expression, and multilingual capabilities. Optimized for high-fidelity applications like voiceovers and audiobooks.
Speech-2.6 TurboText-to-Audio (T2A) that offers voice synthesis, emotional expression, and multilingual capabilities. Optimized for high-fidelity applications like voiceovers and audiobooks.
Video UpscaleVideo Upscaling from Topaz Labs

Output