Explore

I want to…

Restore images

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

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

Updated 2.4K runs

✨Stable Diffusion 3 w/ ⚡InstantX's ControlNet Canny🖼️

Updated 72 runs

Updated 82 runs

Transcribe saxophone solos directly from audio

Updated 138 runs

High resolution image Upscaler and Enhancer. Use at ClarityAI.co. A free Magnific alternative. Twitter/X: @philz1337x

Updated 2.5M runs

Updated 78 runs

Real-Time Open-Vocabulary Object Detection using the xl weights

Updated 36 runs

Updated 336 runs

MusicGen running on an a40 with 60 seconds max duration

Updated 29 runs

https://civitai.com/models/317902/t-ponynai3

Updated 15 runs

A model for experimenting with all the SD3 settings. Non-commercial use only unless you have a Stability AI membership.

Updated 1.3K runs

Updated 161 runs

Detects if a picture has anime face.

Updated 18 runs

Mobius, a diffusion model that pushes the boundaries of domain-agnostic debiasing and representation realignment

Updated 219 runs

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

Updated 324K runs

Omni-Zero: A diffusion pipeline for zero-shot stylized portrait creation.

Updated 366 runs

DOVER video quality assessment tool, assigning videos both aesthetic and technical quality scores

Updated 13 runs

Generate Product photography backgrounds using Stable Diffusion

Updated 79 runs

Generate high resolution image

Updated 416 runs

A text-to-image model with greatly improved performance in image quality, typography, complex prompt understanding, and resource-efficiency

Updated 139.8K runs

DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation. Hologram optimized

Updated 182 runs

Transfer learning models for music classification by genres, moods, and instrumentation

Updated 8.1K runs

🫦 Realistic facial expression manipulation (lip-syncing) using audio or video

Updated 255 runs

MusePose: a Pose-Driven Image-to-Video Framework for Virtual Human Generation.

Updated 168 runs

GLM-4V is a multimodal model competitive with GPT-4o and other top models.

Updated 775 runs

Super bold line portrait illustrations. Best in monochrome with simple prompts.

Updated 4K runs

Super fast clothing (and face) segmentation and masking with erosion and dilation capability.

Updated 3.8K runs

The best Pony-SDXL models! Current one is based on Pony Realism.

Updated 14.8K runs

ZavyChromaXL v7, a high contrast and colorful SDXL fine-tune

Updated 550 runs

MARS5, a fully open-source (commercially usable) voice-cloning/TTS with break-through prosody and realism.

Updated 134 runs

Make MS Paint images, a lora trained by aimingfail

Updated 470 runs

A mid-century Japanese block print style

Updated 245 runs

A rough sketch style manga

Updated 66 runs

A manga style

Updated 34 runs

A sketch manga style

Updated 39 runs

A watercolor style painting model that does impressionism well and lends itself to anime.

Updated 29 runs

Stylized sketch anime model that has a bit of a watercolor undertone to it

Updated 79 runs

An anime style

Updated 36 runs

A style that creates a paint wash, great for anime.

Updated 45 runs

A style model, ligne claire esque with eastern influence

Updated 32 runs

A very blocky and bold cartoon style with some anime elements. You should use daiton style to trigger the image generation.

Updated 209 runs

Updated 51 runs

A model that makes a soft and quiet world. Can use "daiton" as a trigger but it isn't needed.

Updated 203 runs

Detect hate speech or toxic comments in tweets/texts

Updated 472 runs

# Interior Decoration Space Scaling - First Use Case

Updated 56 runs

A tiny model for testing out Cog

Updated 1K runs

Updated 381 runs

Updated 241 runs

Updated 19 runs

nsdxl

Updated 58 runs