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 petitions suitable for sending to the UK government

Updated 108 runs

Fine-grained Image Captioning with CLIP Reward

Updated 296.1K runs

pixray text2image (future branch)

Updated 24.9K runs

face alignment using stylegan-encoding

Updated 5.1K runs

Convert image or video of your face to anime

Updated 4.8K runs

Generate art from text prompts. Based on kvfrans/clipdraw.

Updated 895 runs

Removes specified objects from image

Updated 17K runs

Removes specified objects from image

Updated 899 runs

An open-source model for program synthesis. Competitive with OpenAI Codex.

Updated 1.2K runs

Uses pixray to generate an image from text prompt

Updated 1.4M runs

Draws an abstract sketch of an object

Updated 9K runs

Classifies images with ResNet-50

Updated 183 runs

Classifies images with ResNet-50

Updated 8.8K runs

A 1.4B parameter text2im model from CompVis, finetuned on CLIP text embeds and curated data.

Updated 45.5K runs

Facial Expression Recognition using Residual Masking Network

Updated 16K runs

Transfer the texture/style of one image onto another

Updated 7.7K runs

A simple Hebrew Diacritizer

Updated 130 runs

Updated 272 runs

Detect Animals, Vehicles and Humans in Camera Trap Imagery

Updated 566 runs

Plugging Visual Controls in Text Generation

Updated 1.5K runs

Updated 17 runs

Practical Blind Denoising via Swin-Conv-UNet and Data Synthesis

Updated 99.2K runs

Music inpainting of melody and chords

Updated 8.6K runs

Nonlinear Activation Free Network for Image Restoration

Updated 1.4M runs

Zero shot Sound separation by arbitrary query samples

Updated 52.1K runs

Multi-Axis MLP for Image Processing

Updated 517.1K runs

Detect and simplify the contours of a binary image

Updated 233 runs

Super-resolves an LR video frame (ultra-wide) using a reference video frame (wide-angle)

Updated 14.3K runs

Homage to the Pixel: text prompt to 6 color squares

Updated 9.4K runs

[CVPR 2022] Unsupervised Image-to-Image Translation with Generative Prior

Updated 1.2K runs

bare pixray for API use

Updated 11.6K runs

Design Your Hair by Text and Reference Image

Updated 294.3K runs

A Steerable Model for Bach Chorales Generation

Updated 844 runs

One-shot (any-to-any) Voice Conversion

Updated 6.3K runs

Online demo for "Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation"

Updated 1.9K runs

A model for testing pydantic cog that yields images one word at a time.

Updated 129 runs

Image Style Transfer with Text Condition

Updated 25.9K runs

Synthesize drawings to match a text prompt

Updated 5.6K runs

A model for testing pydantic cog that generates images.

Updated 410 runs

A test model that generates Haiku (and yields output one word a time)

Updated 107 runs

Clip-Guided Diffusion Model for Image Generation

Updated 4.5K runs

GLIDE-text2im w/ humans and experimental style prompts.

Updated 9.2K runs

Updated 565 runs

A fork of pixray/pixray for trying out Cog's new Predictor API

Updated 59 runs

Grad-CAM visualizations for Align before Fuse

Updated 3.7K runs

Updated 75 runs

GLIDE from OpenAI finetuned on roughly 30M more samples. See `laionide-v3` for the latest.

Updated 3.8K runs

Transcribes piano audio and makes it into a cool video

Updated 218 runs

Masked-attention Mask Transformer for Universal Image Segmentation

Updated 658 runs