I want to…

Restore images

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

Caption images

Models that generate text prompts and captions from images

Upscale images

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

Train a language model

Language models that you can fine-tune using Replicate's training API.

Make 3D stuff

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

Latest models

🗣️ TalkNet-ASD: Detect who is speaking in a video

Updated 3 runs

Turn a face into a sticker

Updated 23.2K runs

https://www.interioraidesigns.com. Take a picture of your room and see how your room looks in different themes. Remodel your room today.

Updated 7K runs

Updated 199 runs

Lanne M1 is the first language model produced by Lanne Tech. It is based on +70B of parameters. With performance equivalent to GPT3.5.

Updated 101 runs

State-of-the-art text to image with turbo speed

Updated 213 runs

Real-Time Open-Vocabulary Object Detection

Updated 934 runs

Check our flamel.app (this model will be added to flamel)

Updated 106 runs

Generate a model with a garment faster if you have a mask image

Updated 103 runs

Make stickers with AI. Generates graphics with transparent backgrounds.

Updated 46.2K runs

Updated 19 runs

Juggernaut XL v9

Updated 1.4K runs

Surya is a document OCR toolkit that does:

Updated 40 runs

sdxl-lcm finetuned for Kids Colouring Pages

Updated 87 runs

Updated 54 runs

Updated 43 runs

Generate 3D assets using text descriptions

Updated 780 runs

Run any ComfyUI workflow. Guide: https://github.com/fofr/cog-comfyui

Updated 29.2K runs

DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation

Updated 6.9K runs

Turn anything into an abstract fine art masterpiece 🎨

Updated 82 runs

Virtual dressing room

Updated 1.4K runs

Updated 13 runs

State-of-the-art text to image

Updated 4.3K runs

Generates 3D assets from images

Updated 1.9K runs

Try clothes on a model

Updated 29 runs

Generate models with a garment

Updated 64 runs

Try clothes on a model when you already have an upper body mask

Updated 20 runs

Only makes segmentations for further processing

Updated 19 runs

InstantID. ControlNets. More base SDXL models. And the latest ByteDance's ⚡️SDXL-Lightning !⚡️

Updated 1.2K runs

Scribbled art drawings style

Updated 230 runs

SDXL lightning mult-controlnet, img2img & inpainting

Updated 297 runs

Updated 204 runs

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

Updated 3K runs

PLEASE DONT USE LATEST VERSIONS, I AM TESTING THINGS, Updated -> Realistic_Vision_V6.0_B1 || Inpainting || multi-controlnet || single-controlnet || ip-adapter || ip adapter face || ip adapter plus || No ip adapter

Updated 122.2K runs

ProteusV0.4: The Style Update

Updated 2.5K runs

Updated 49 runs

Lightweight multimodal model for visual question answering, reasoning and captioning

Updated 46 runs

Updated 239 runs

Simple video chroma keying

Updated 20 runs

Multilingual E5-small language embedding model

Updated 1 run

Multilingual E5-large language embedding model

Updated 6 runs

Multilingual E5-large language embedding model

Updated 2 runs

Updated 145 runs

Tea Segmentation Demo

Updated 24 runs

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

Updated 53 runs

OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement

Updated 43 runs

Instant ID with ControlNet and LCM

Updated 212 runs

Updated 58 runs

Updated 516 runs

AnimateDiff video to video

Updated 158 runs