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

live portrait with audio

Updated 12K runs

ECCV2022 Quick background removal

Updated 187 runs

"MusiConGen: Rhythm and chord control for Transformer-based text-to-music generation"

Updated 102 runs

A ready to use image to image workflow of flux

Updated 32K runs

Updated 45.7K runs

Gemma2 2b Instruction-tuned variant by Google

Updated 35 runs

Gemma2 2b by Google

Updated 33.9K runs

AuraSR v2: Second-gen GAN-based Super-Resolution for real-world applications

Updated 1.5K runs

MT3: Multi-Task Multitrack Music Transcription

Updated 55 runs

Generate high resolution image

Updated 1.3K runs

Segment Anything 2 (SAM2) by Meta - Automatic mask generation

Updated 5.6K runs

SAM 2: Segment Anything v2 (for Images)

Updated 6.6K runs

Real-ESRGAN Upscale with AI Face Correction

Updated 513.7K runs

Change the background on an image and relight the scene.

Updated 916 runs

LLaMA 3.1-8B, finetuned on a synthetic OCR dataset for superior OCR correction.

Updated 20 runs

Updated 49 runs

A chat-bot that specialises in Space/Aeronautics knowledge.

Updated 17 runs

multilingual-e5-large-instruct: A multi-language text embedding model with custom query instructions.

Updated 15.1K runs

moondream2 is a small vision language model designed to run efficiently on edge devices

Updated 216.6K runs

Generate panoramic image based on text prompts or image.

Updated 168 runs

Huggingface Diffusers: SDv1.4/1.5/2.0/2.1 finetuner

Updated 11 runs

Combines inpainting and outpainting for image editing.

Updated 213 runs

Inpaint a selected area of an image using controlnet union for SDXL.

Updated 250 runs

Outpaint an image using controlnet union for SDXL.

Updated 1.3K runs

Bilateral Reference for High-Resolution Dichotomous Image Segmentation (CAAI AIR 2024)

Updated 8.8K runs

A fully open-sourced, large flow-based text-to-image generation model

Updated 400 runs

LLM-powered applications are susceptible to prompt attacks, which are prompts intentionally designed to subvert the developer’s intended behavior of the LLM

Updated 22 runs

Updated 27 runs

Personalized Image Filters at Your Fingertips

Updated 92 runs

Real-ESRGAN with optional face correction and adjustable upscale

Updated 56M runs

Real-ESRGAN for image upscaling on an A100

Updated 11.9M runs

Updated 105 runs

An SDXL model Finetuned for style on Marker-Style Sketches

Updated 486 runs

An SDXL model Finetuned for style on a bespoke dataset of Stylized Illustrations

Updated 833 runs

sound separation with demucs

Updated 16.8K runs

Fork of https://replicate.com/zsxkib/ic-light that allows any image resolution

Updated 4.7K runs

Upscale pictures and videos using the nunif repo (formerly waifu2x).

Updated 263 runs

PrometheusV1 is presumed to be the first full rank finetune of Playground v2.5

Updated 135 runs

Updated 70 runs

Updated 2.3K runs

ProteusV0.5 is the latest full release built as a sophisticated enhancement over OpenDalleV1.1

Updated 3.1K runs

Meta's flagship 405 billion parameter language model, fine-tuned for chat completions

Updated 4M runs

Updated 286 runs

Updated 469 runs

dolly-v2-12b, just for testing

Updated 15 runs

Accelerated transcription, word-level timestamps and diarization with whisperX large-v3 for large audio files. Fork of victor-upmeet/whisperx-a40-large with diarization fixed and group_segments implemented

Updated 1.5K runs

A 14B parameter, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense pro

Updated 73 runs

Ultra high resolution images (up to 4096x4096) based on Stable Cascade

Updated 8.1K runs

Seamlessly create stunning product shots by blending with inspirational references for a fresh, modern look

Updated 227 runs

Detect hate speech or toxic comments in tweets/texts

Updated 67.3K runs