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

Generate videos by interpolating the latent space of Stable Diffusion

Updated 991 runs

Neurealist Tarot (v_2) Replicate Version: a Tarot card generating model trained by A.C.T. SOON® over SD v1-5, from custom data and class sets, and via Dreambooth/Cog

Updated 435 runs

Updated 57 runs

RaCC0on Generator

Updated 261 runs

Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding

Updated 6.1K runs

Trained to create rubber ducks. That is all.

Updated 540 runs

Fine-tuned GPT-J 6B model on the Alpaca dataset

Updated 982 runs

Stable Diffusion v2-1-unclip Model

Updated 2.3K runs

Updated 237 runs

Make any Image Talk. The image must have a human face and should be of dimensions strictly 256x256.

Updated 8.1K runs

Predictive CFD from 2D input

Updated 198 runs

Some scrappy experiments 🫣

Updated 722 runs

Modify images with canny edge detection and Deliberate model twitter: @philz1337x

Updated 1.1M runs

Deep Exemplar-based Video Colorization Simply put, the mission of this project is to colorize and restore old images and film footage. We'll get into the details in a bit, but first let's see some pretty pictures and videos!

Updated 398 runs

One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale

Updated 1.2K runs

Replicate port of https://huggingface.co/Envvi/Inkpunk-Diffusion. Finetuned Stable Diffusion model trained on dreambooth. Vaguely inspired by Gorillaz, FLCL, and Yoji Shinkawa.

Updated 3.4K runs

Transformers implementation of the LLaMA language model

Updated 99.2K runs

Updated 562.4K runs

Dream Shaper stable diffusion

Updated 1.3M runs

A Vision-Language Model with An Ensemble of Experts

Updated 1.7K runs

Updated 421 runs

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

Updated 92.9M runs

ZoeDepth: Combining relative and metric depth

Updated 4.6M runs

mixed stable diffusion model

Updated 30K runs

Realistic vision + inpainting + controlnet pose

Updated 25K runs

LoRA Inference model with Stable Diffusion

Updated 130.7K runs

Updated 5.1K runs

Updated 11.5K runs

Updated 7.6K runs

https://huggingface.co/wavymulder/portraitplus

Updated 7.2K runs

Updated 6.1K runs

Finetuned Stable-diffusion from Gerry Anderson Supermarionation

Updated 1.9K runs

Spotify's Basic Pitch Model

Updated 1.1K runs

Generate an image by specifying a different text prompt for each region

Updated 779 runs

LoRA, fp16 vintedois-diffusion-v0-1

Updated 5.7K runs

A model I copied to blur an image

Updated 253 runs

Change voice for spoken text

Updated 73.6K runs

The Pastel Model with highres upscale

Updated 35.5K runs

Fusing Diffusion Paths for Controlled Image Generation

Updated 2.2K runs

Updated 42.7K runs

Shiba stable diffusion model

Updated 691 runs

Modify images with a prompt while preserving their structure

Updated 63.2K runs

Modify images with humans using pose detection

Updated 174.8K runs

Modify images using canny edge detection

Updated 828.1K runs

Exploring the training and use of DreamBooth, with Bart as a subject

Updated 305 runs

To explore stablebooth (training and prompts) trained on pictures of James!

Updated 262 runs

high-quality highly detailed anime stylized latent diffusion model

Updated 32.1K runs

Updated 333 runs

Fine-tuned model based on Nick St. Pierre's latest Midjourney model!

Updated 2.8K runs