I want to…

Caption images

Models that generate text prompts and captions from images

Make 3D stuff

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

Restore images

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

Train a language model

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

Upscale images

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

Latest models

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

Updated 66 runs

Updated 99 runs

Updated 25.4K runs

Merge two images together with a prompt

Updated 475 runs

Updated 30 runs

Honeycomb NLQ Generator

Updated 151 runs

Updated 66 runs

Updated 174 runs

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

Updated 8.1K runs

Updated 180 runs

SDXL-Lightning by ByteDance, is a fast text-to-image model that makes high-quality images in 4 steps

Updated 74.6K runs

Updated 36 runs

hello-world from cog example

Updated 32 runs

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

Updated 3.1K runs

Updated 48 runs

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

Updated 205 runs

7B base version of Google’s Gemma model

Updated 346 runs

2B base version of Google’s Gemma model

Updated 114 runs

7B instruct version of Google’s Gemma model

Updated 2.6K runs

2B instruct version of Google’s Gemma model

Updated 354 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 81 runs

POC CUDA implementation of an rgb2grayscale function

Updated 78 runs

SDXL Concept Art and Illustrations

Updated 331 runs

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

Updated 30 runs

MusicGen stereo-medium model fine-tuned on Bbongjjak(뽕짝), the Korean modern electronic pop music genre, with the text token 'Bbongjjak'.

Updated 63 runs

Fine-tune MusicGen small, medium and melody models. Also stereo models available.

Updated 1.8K runs

Trained Stable Diffusion XL Lora With Black Male Hairstyles

Updated 79 runs

Updated 23.3K runs

A SDXL inpainting model that can be used for Replicate finetuning

Updated 433 runs


Updated 87 runs

Realism photo with RealVisXl v4.0 ( Realistic Vision with Stable Diffusion XL )

Updated 1.2K runs

Updated 78 runs

Photorealism with RealVisXL V4.0

Updated 1.7K runs

Visual instruction tuning towards large language and vision models with GPT-4 level capabilities

Updated 4.6M runs

Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Updated 235.5K runs

Split a single video, into it's individual clips by detecting cuts.

Updated 54 runs

Updated 448 runs

Updated 71 runs

majicMIX realistic V7 support civitai lora,text2image,image2image

Updated 520 runs

LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation

Updated 248 runs

Accelerated transcription, word-level timestamps and diarization with whisperX large-v3 for large audio files

Updated 715 runs

Accelerated transcription, word-level timestamps and diarization with whisperX large-v3

Updated 58.5K runs

Utilize the capabilities of SD WebUI, including Hires. fix and plenty of extensions (e.g. ADetailer)

Updated 3.1K runs

The Mixtral-8x7B-instruct-v0.1 Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts tuned to be a helpful assistant.

Updated 1.8M runs

Pocket-Sized Multimodal AI For Content Understanding and Generation

Updated 244 runs

Stable Diffusion XL fine-tuned to create images based on Le Corbusier's architectural style.

Updated 53 runs

⚡️ Fast audio transcription | whisper v3 | speaker diarization | word level timestamps | prompt

Updated 122.5K runs

Mamba 2.8B state space language model fine tuned for chat

Updated 49 runs

Updated 44 runs

MagicDance: Realistic Human Dance Video Generation with Motions & Facial Expressions Transfer

Updated 333 runs