Explore

I want to…

Upscale images

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

Restore images

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

Flux fine-tunes

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

Make 3D stuff

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

Latest models

DUSt3R: Geometric 3D Vision Made Easy

Updated 418 runs

Sentiment Analysis with Texts

Updated 4.8K runs

A wrapper around bel-tts

Updated 1.4K runs

Turn a face into a sticker

Updated 1.2M runs

Updated 252 runs

Juggernaut XL v9

Updated 1.3M runs

Surya is a document OCR toolkit that does:

Updated 4.7K runs

sdxl-lcm finetuned for Kids Colouring Pages

Updated 1.1K runs

Updated 130 runs

Turn anything into an abstract fine art masterpiece 🎨

Updated 371 runs

Generates 3D assets from images

Updated 2.7K runs

Scribbled art drawings style

Updated 817 runs

SDXL lightning mult-controlnet, img2img & inpainting

Updated 7.5K runs

dreamshaper-xl-lightning is a Stable Diffusion model that has been fine-tuned on SDXL

Updated 86.8K runs

ProteusV0.4: The Style Update

Updated 110.4K runs

Updated 168 runs

Lightweight multimodal model for visual question answering, reasoning and captioning

Updated 3.9K runs

Updated 81.3K runs

Simple video chroma keying

Updated 38 runs

Multilingual E5-small language embedding model

Updated 46 runs

Multilingual E5-large language embedding model

Updated 20 runs

Multilingual E5-large language embedding model

Updated 536 runs

Updated 3.4K runs

Tea Segmentation Demo

Updated 26 runs

Function calling LLM that surpasses the state-of-the-art in function calling capabilities

Updated 61 runs

OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement

Updated 101 runs

Updated 81 runs

AnimateDiff video to video

Updated 540 runs

Updated 1.3K runs

SDXL tuned on Vsevolod Ivanov paintings

Updated 779 runs

Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild. This is the SUPIR-v0F model and does NOT use LLaVA-13b.

Updated 10.3K runs

Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild. This is the SUPIR-v0Q model and does NOT use LLaVA-13b.

Updated 7.3K runs

Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild. This version uses LLaVA-13b for captioning.

Updated 158.4K runs

POC implementation of Depth-anything to produce a 3D SBS video

Updated 185 runs

E5-mistral-7b-instruct language embedding model

Updated 627 runs

Untamed

Updated 153 runs

Merge two images together with a prompt

Updated 4.7K runs

Honeycomb NLQ Generator

Updated 181 runs

ProteusV0.4: The Style Update - enhances stylistic capabilities, similar to Midjourney's approach, rather than advancing prompt comprehension

Updated 130.7K runs

hello-world from cog example

Updated 34 runs

A collection of anime stable diffusion models with VAEs and LORAs.

Updated 3.6K runs

Get the width, height, and duration in seconds from a video

Updated 220 runs

7B base version of Google’s Gemma model

Updated 7.2K runs

2B base version of Google’s Gemma model

Updated 1.6K runs

7B instruct version of Google’s Gemma model

Updated 66.4K runs

2B instruct version of Google’s Gemma model

Updated 92.8K runs

DreamCraft3D is a text and image to 3D model. Dreamcraft3D uses DeepFloyd IF and Stable Zero123, non-commercial research-only models. Please make sure you read and abide to the relevant licenses before using it.

Updated 481 runs

CUDA implementation of an rgb2grayscale function

Updated 105 runs

Automatically remove "dead-air" from videos with a loudness and motion threshold.

Updated 35 runs