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.

View all official models

I want to…

Upscale images

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

Make 3D stuff

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

Restore images

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

Make videos with Wan2.1

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

Control image generation

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

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.

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.

Use FLUX fine-tunes

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

Latest models

Real-ESRGAN: Real-World Blind Super-Resolution

Updated 2.4M runs

Learning Adapters towards Controllable for Text-to-Image Diffusion Models

Updated 3.9K runs

Modify images using normal maps

Updated 330.6K runs

Modify images using depth maps

Updated 678.7K runs

High performance and lightweight object detection models

Updated 23.2K runs

Edit an image using features from diffusion models

Updated 8.7K runs

Modify images using M-LSD line detection

Updated 9.7M runs

Modify images using semantic segmentation

Updated 166.5K runs

Robust Monocular Depth Estimation

Updated 637.5K runs

LoRA model trainer, advanced version

Updated 2.9K runs

LoRA model trainer with presets for faces, objects, and styles

Updated 33.1K runs

Generate detailed images from scribbled drawings

Updated 38.3M runs

Modify images using HED maps

Updated 550.4K runs

LoRA, fp16 Foto-Assisted-Diffusion-FAD_V0

Updated 7.4K runs

Gradient-Based Discrete Optimization for Prompt Tuning and Discovery

Updated 656 runs

3D Photography using Context-aware Layered Depth Inpainting

Updated 6.1K runs

Zero-shot Image-to-Image Translation

Updated 6.3K runs

A diffusion model for generating human motion video from a text prompt

Updated 14.2K runs

Stable Diffusion, accelerated

Updated 3.1K runs

A deep learning approach to remove background & adding new background image

Updated 771K runs

Lucid Sonic Dreams syncs StyleGAN XL -generated visuals to music

Updated 2.5K runs

A crazy model which maybe does nothing, maybe does something, but its supposed to be about football.

Updated 522 runs

Dreambooth finetuning of Stable Diffusion (v1.5.1) on Avatar art style by Lambda Labs

Updated 586 runs

GTA5 Artwork Diffusion via Dreambooth

Updated 4.9K runs

Generate characters from Avatar

Updated 176 runs

Lucid Sonic Dreams syncs GAN-generated visuals to music

Updated 4.6K runs

Cut and Learn for unsupervised object detection and instance segmentation

Updated 2.5K runs

Generate t-shirt logos with stable-dfffusion

Updated 182.4K runs

Text-to-audio generation with latent diffusion models

Updated 37.7K runs

Audio Reactive Stable Diffusion

Updated 5.7K runs

Add colours to old images

Updated 428.7K runs

Add colours to old video footage.

Updated 5.5K runs

This is the OpenJourney img2img model

Updated 89.2K runs

Descriptive stable diffusion prompts generation using GPT2

Updated 607 runs

RealBasicVSR: Investigating Tradeoffs in Real-World Video Super-Resolution

Updated 9.1K runs

High accuracy depth maps from pairs of stereo images

Updated 771 runs

Shows what CLIP looks at in an image given text

Updated 748 runs

About Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation

Updated 2.9K runs

Create variations of an image while preserving shape and depth

Updated 58.9K runs

Assess the quality of an image

Updated 150.6K runs

Portraits with stable-diffusion

Updated 24.2K runs

Generate beautiful images with simple prompts

Updated 247.2K runs

Edit images with human instructions

Updated 914.9K runs

Edit images with human instructions

Updated 41.8K runs

high-quality, highly detailed anime-style Stable Diffusion models

Updated 3.3M runs

Create variations of an image while preserving shape and depth.

Updated 7.9K runs

Detects one paragraph of text in an image.

Updated 19.9K runs

Turn two prompts into one image

Updated 325 runs

Point-E: A System for Generating 3D Point Clouds from Complex Prompts

Updated 8.8K runs