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

RunDiffusion FX Photorealistic model, developed by RunDiffusion.

Updated 41.3K runs

Updated 447 runs

Split a video into frames

Updated 12.7K runs

LLaMA 1.0 (13B) model fine-tuned for academic use cases like text classification. Use at your own risk. Not to be confused with the vision model.

Updated 489 runs

Stable Diffusion inference using Keras model

Updated 97 runs

Updated 4.3K runs

Convert a set of frames to a video

Updated 1.5K runs

Diffusion-based semantic image editing with mask guidance

Updated 401 runs

Kandinsky 2.1 Diffusion Model

Updated 84.1K runs

SDRV_2.0

Updated 14.9K runs

Stable Diffusion fine tuned on Midjourney v4 images.

Updated 11.9M runs

Age prediction using CLIP - Patched version of `https://replicate.com/andreasjansson/clip-age-predictor` that works with the new version of cog!

Updated 167.6K runs

Persian (Farsi) Handwritten Digit Detector

Updated 83 runs

Transform your text into a beautiful two-tone color gradient that represents your emotions.

Updated 389 runs

A "Hello World" model for me to get to grips with `cog` and Replicate

Updated 43 runs

Updated 37 runs

Diffusion Models as Text Painters

Updated 1.7K runs

Prompt-free Diffusion

Updated 738 runs

Generate a new image from an input image with AbsoluteReality v1.0

Updated 273.3K runs

Generate a new image given any input text with AbsoluteReality v1.0

Updated 264.4K runs

Generate a new image from an input image with DreamShaper V6

Updated 132.6K runs

Generate a new image given any input text with DreamShaper V6

Updated 421.9K runs

Generate a new image from an input image with Babes 2.0

Updated 1.4M runs

Generate a new image from an input image with RPG V4

Updated 2.2K runs

Generate a new image from an input image with URPM v1.3

Updated 2.5K runs

Generate a new image from an input image with Deliberate v2

Updated 9.2K runs

Generate a new image from an input image with Edge Of Realism - EOR v2.0

Updated 538.1K runs

Generate a new image from an input image with Realistic Vision V2.0

Updated 54.5K runs

Generate a new image given any input text with Babes 2.0

Updated 25.8K runs

Generate a new image given any input text with RPG V4

Updated 58.3K runs

Generate a new image given any input text with URPM v1.3

Updated 54.3K runs

Generate a new image given any input text with Deliberate v2

Updated 627.6K runs

Generate a new image given any input text with Edge Of Realism - EOR v2.0

Updated 129.5K runs

Generate a new image given any input text with Realistic Vision V2.0

Updated 525.9K runs

This is a language model that can be used to obtain document embeddings suitable for downstream tasks like semantic search and clustering.

Updated 2.2M runs

Real-World Super-Resolution Models for Animation Videos

Updated 10.1K runs

This model can detect clothing using a custom state of the art clothing segmentation algorithm.

Updated 3.2K runs

Training-free Controllable Text-to-Video Generation

Updated 2.1K runs

This model is actually: prompthero / openjourney-v4

Updated 279 runs

Regression of musical arousal and valence values

Updated 5.5K runs

Classification of music approachability and engagement

Updated 10.2K runs

An EfficientNet for music style classification by 400 styles from the Discogs taxonomy

Updated 123.5K runs

My own personal try of Stable Diffusion

Updated 41 runs

Updated 32.1K runs

Updated 38 runs

A multi-input ControlNet model. Pass in control images and set the weights.

Updated 248 runs

Generate subtitles (.srt and .vtt) from audio files using OpenAI's Whisper models.

Updated 5.1K runs

Generating Conditional 3D Implicit Functions

Updated 14.8K runs

Updated 27.5K runs

Image captioning via vision-language models with instruction tuning

Updated 542.9K runs