Explore

Fine-tune FLUX fast

Customize FLUX.1 [dev] with the fast FLUX trainer on Replicate

Train the model to recognize and generate new concepts using a small set of example images, for specific styles, characters, or objects. It's fast (under 2 minutes), cheap (under $2), and gives you a warm, runnable model plus LoRA weights to download.

Official models

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

I want to…

Make videos with Wan2.1

Generate videos with Wan2.1, the fastest and highest quality open-source video generation model.

Try for free

Get started with these models without adding a credit card. Whether you're making videos, generating images, or upscaling photos, these are great starting points.

Restore images

Models that improve or restore images by deblurring, colorization, and removing noise

Upscale images

Upscaling models that create high-quality images from low-quality images

Enhance videos

Models that enhance videos with super-resolution, sound effects, motion capture and other useful production effects.

Detect objects

Models that detect or segment objects in images and videos.

Make 3D stuff

Models that generate 3D objects, scenes, radiance fields, textures and multi-views.

Use FLUX fine-tunes

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

Control image generation

Guide image generation with more than just text. Use edge detection, depth maps, and sketches to get the results you want.

Latest models

LBM: Latent Bridge Matching for Fast Image-to-Image Translation

Updated 13 runs

Generate expressive, natural speech with Resemble AI's Chatterbox.

Updated 68 runs

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

Updated 67.2K runs

Latest Pony Realism Model. Try it with WEIGHTS on creatorframes.com

Updated 2.7K runs

Updated 29.7K runs

A Universal Customization Method for Both Single and Multi-Subject Conditioning

Updated 30 runs

Remove any object from video - fast.

Updated 16 runs

Claude Sonnet 4 is a significant upgrade to 3.7, delivering superior coding and reasoning while responding more precisely to your instructions

Updated 113.4K runs

Change the aspect ratio of any photo using AI (not cropping)

Updated 948 runs

Change the aspect ratio of any video up to 30 seconds long, outputs will be 720p

Updated 1.3K runs

OpenAI's first o-series reasoning model

Updated 14.1K runs

OpenAI's fast, lightweight reasoning model

Updated 5K runs

This is the fastest Flux Dev endpoint in the world.

Updated 34.9K runs

Low latency, low cost version of OpenAI's GPT-4o model

Updated 1.5M runs

OpenAI's high-intelligence chat model

Updated 99.1K runs

OpenAI's Flagship GPT model for complex tasks.

Updated 10.5K runs

Fast, affordable version of GPT-4.1

Updated 766.9K runs

Fastest, most cost-effective GPT-4.1 model from OpenAI

Updated 7.4K runs

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

Updated 10.5K runs

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

Updated 22.8K runs

Google's Imagen 4 flagship model

Updated 369.6K runs

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

Updated 212.1K runs

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

Updated 1.1M runs

Transforms any rhythmic sound—a drum kit, beatboxing, a toy drum, even drumming on your belly—into a pro-quality performance on Zohar's studio drum kit.

Updated 27 runs

Train subjects or styles faster than ever

Updated 9K runs

Updated 46 runs

FLUX.1-Dev Multi LoRA Explorer

Updated 1.4M runs

An optimized version of sdxl-lightning from Bytedance that is more than 2x faster and 2x cheaper

Updated 77 runs

Run any ComfyUI workflow. Guide: https://github.com/replicate/cog-comfyui

Updated 3.8M runs

This is VACE-14B model optimised with pruna ai. Wan2.1 VACE is an all-in-one model for video creation and editing.

Updated 6.9K runs

Cog to turn minimally-formatted plaintext into pdfs (using tex on the backend)

Updated 112 runs

Become a character, in style

Updated 4.8K runs

Scaling Diffusion Models for High Resolution Textured 3D Assets Generation

Updated 11.8K runs

Updated 281 runs

Updated 13 runs

Fine-tune FLUX.1-dev using ai-toolkit

Updated 668.4K runs

Turn yourself into a renaissance-era painting for those renaissance moments

Updated 1.2K runs

FLUX Kontext max with list input for multiple images

Updated 14.6K runs

Generate 5s and 10s videos in 1080p resolution

Updated 452.8K runs

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

Updated 818.7K runs

Generate 5s and 10s videos in 720p resolution

Updated 40.4K runs

This is an optimised version of the FLUX.1 [schnell] model from Black Forest Labs made with Pruna. We achieve a ~3x speedup over the original model with minimal quality loss.

Updated 2M runs

Merge multiple images into clean horizontal or vertical strips with precise alignment and sizing controls.

Updated 116 runs

An experimental model with FLUX Kontext Pro that can combine two input images

Updated 22.3K runs

Remove all text from an image with FLUX.1 Kontext

Updated 3.8K runs

This model generates pose variation of a cartoon character. It preserves the cartoon identity. Use this model to augment training dataset for any cartoon character created through AI. The augmented dataset can be used to train a LoRA model.

Updated 5.3K runs