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

Convert mobile videos to NeRF-ready colmap files

Updated 407 runs

Prompt-to-prompt image editing with cross-attention control

Updated 2.3K runs

3 Million Runs! AI Photorealistic Image Super-Resolution and Restoration

Updated 3.6M runs

Archer on Stable Diffusion via Dreambooth

Updated 8.4K runs

Updated 87.4K runs

Updated 19.9K runs

Uses pixray to generate an image from text prompt

Updated 223.8K runs

Turn any description into pixel art

Updated 104.1K runs

Implicit neural differentiable FM synthesizer

Updated 395 runs

Updated 160.7K runs

Turn any description into wallpaper tiles

Updated 21.3K runs

Pixray with custom settings

Updated 59K runs

Uses pixray with raw settings.

Updated 29.2K runs

A pixray tool for 24x24 pixelart

Updated 1.6K runs

Stable diffusion, but with more powerful in-painting & out-painting capabilities

Updated 13.5K runs

stable-diffusion with v1-5 checkpoint

Updated 35.8K runs

Stable Diffusion with Aesthetic Gradients

Updated 356 runs

Method for generating bizarre looking videos from a series of language descriptions of the video. From the Bot Intelligence Group at CMU: Peter Schaldenbrand, Zhixuan Liu, & Jean Oh

Updated 8.5K runs

Highly Accurate Dichotomous Image Segmentation (ECCV 2022)

Updated 5K runs

Generate image from text by guiding a denoising diffusion model. Inference is somewhat slow.

Updated 43.1K runs

Generate images from text quickly. See https://replicate.com/afiaka87/laionide-v2 for a new checkpoint.

Updated 7.3K runs

The predecessor to DALLE-2, GLIDE (filtered) with faster PRK/PLMS sampling.

Updated 18.6K runs

Text-Driven Manipulation of StyleGAN Imagery

Updated 1.3M runs

Updated 1.1M runs

Updated 249.7K runs

Stable Diffusion on Danbooru images

Updated 1.1M runs

mediapipe facial landmark detection demo by Marlene Mhangami

Updated 449 runs

image to image style transfer using STROTSS loss

Updated 8.9K runs

high-resolution piano transcription system: detects piano notes from audio

Updated 4.3K runs

stable-diffusion with negative prompts, more scheduler

Updated 65.4K runs

An Adversarial Approach for Picture Colorization

Updated 337.8K runs

Emotional conditioned music generation using transformer-based model.

Updated 3.2K runs

Styledreams -- CLIP x Stylegan2

Updated 4.1K runs

Teach Machines to Paint

Updated 2.1K runs

Text-Guided Diverse Face Image Manipulation

Updated 8.6K runs

Styled text-to-drawing synthesis method.

Updated 2.1K runs

Four-bar drum loop generation

Updated 54.2K runs

image to text generation

Updated 6.7K runs

Scale-Arbitrary Super-Resolution

Updated 21.3K runs

Image to oil painting generation

Updated 6.5K runs

stylegan3 + clip

Updated 6.9K runs

Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation

Updated 9.8K runs

Caricature Generation via StyleGAN Feature Map Modulation

Updated 5.4K runs

Intelligent image scaling to 4x resolution

Updated 40.7K runs

Arbitrary Neural Style Transfer

Updated 426.8K runs

Removes defocus blur in an image

Updated 121.2K runs

Added downloadable subtitles for openai/whisper

Updated 2.2K runs

Image Super-Resolution

Updated 222.6K runs

Image 4x super-resolution

Updated 126.9K runs

Prompt Parrot generates text2image prompts from finetuned distilgpt2

Updated 252.3K runs