3D models

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

alaradirik/dreamgaussian , jd7h/zero123plusplus , adirik/wonder3d , adirik/mvdream , adirik/mvdream-multi-view ...

Streaming language models

Language models that support streaming responses. See https://replicate.com/docs/streaming

meta/llama-2-70b-chat , meta/llama-2-13b-chat , meta/llama-2-7b-chat , yorickvp/llava-13b , fofr/prompt-classifier ...

Super resolution

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

nightmareai/real-esrgan , jingyunliang/swinir , mv-lab/swin2sr , cjwbw/real-esrgan , cjwbw/rudalle-sr ...

Vision models

Multimodal large language models with vision capabilities like object detection and optical character recognition (OCR)

yorickvp/llava-13b , daanelson/minigpt-4 , cjwbw/internlm-xcomposer , joehoover/mplug-owl , lucataco/qwen-vl-chat ...

Latest models

Playground v2 is a diffusion-based text-to-image generative model trained from scratch. Try out all 3 models here

Updated 11 runs

Chest X ray

Updated 6 runs

Create driving poses for magic-animate

Updated 105 runs


Updated 298 runs

BSHM 人像抠图

Updated 401 runs

A fine-tuned SDXL based on GTA V art

Updated 11.4K runs

Kosmos-G: Generating Images in Context with Multimodal Large Language Models

Updated 76 runs

SVD + in-painting

Updated 103 runs

Updated 32 runs

A ~7B parameter language model from Deepseek for SOTA repository level code completion

Updated 13 runs

Updated 87 runs

Updated 1.4K runs

Source: Pclanglais/MonadGPT ✦ Quant: TheBloke/MonadGPT-AWQ ✦ What would have happened if ChatGPT was invented in the 17th century?

Updated 14 runs

Updated 52 runs

Playground v2 is a diffusion-based text-to-image generative model trained from scratch by the research team at Playground

Updated 4.8K runs

Source: fblgit/una-cybertron-7b-v2-bf16 ✦ Quant: TheBloke/una-cybertron-7B-v2-AWQ ✦ A 7B MistralAI based model, best on it's series. Trained on SFT, DPO and UNA (Unified Neural Alignment) on multiple datasets

Updated 15 runs

Inference SDXL with cog including multiple models in 1 instance support.

Updated 1K runs

Generate plasma shader equations

Updated 255 runs

Translate audio while keeping the original style, pronunciation and tone of your original audio.

Updated 124 runs

Updated 75 runs

Convert your videos to DensePose and use it with MagicAnimate

Updated 330 runs

Updated 219 runs

Updated 31.2M runs

Add a watermark to your videos using the power of Replicate brought to you from your friends at FullJourney.AI

Updated 365 runs

GoogleAI: Style Aligned Image Generation via Shared Attention

Updated 366 runs

Extracts motion from video

Updated 66 runs

Remix the music into another styles with MusicGen Chord

Updated 1.4K runs

https://www.photoaistudio.com. Take a picture of your face and instantly get any profile picture you want. Only 1 photo, no training needed.

Updated 2.6K runs

Train your own custom RVC model

Updated 282 runs

A fine-tuned SDXL LoRA trained on Georgia O'keeffe art

Updated 30 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 365 runs

Transcribes any audio file with speaker diarization. *Please check the README*

Updated 19.8K runs

Deliberate V5 Model (Text2Img, Img2Img and Inpainting)

Updated 625 runs

Counterfeit XL v2 Model (Text2Img, Img2Img and Inpainting)

Updated 193 runs

Updated 63 runs

Edit real or generated images

Updated 84 runs

Edit real or generated images

Updated 57 runs

Simple model to make addition and answer is send to supabase

Updated 19 runs

highist resolutioin image

Updated 50 runs

Juggernaut XL v7 Model (Text2Img, Img2Img and Inpainting)

Updated 763 runs

MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

Updated 6.8K runs

Updated 72 runs

Updated 23 runs

Generate color codes for prominent colors in the image

Updated 42 runs

Given two images depicting a source structure and a target appearance, generate an image merging the structure of one image with the appearance of the other

Updated 203 runs

Updated 38 runs

Source: chargoddard/loyal-piano-m7 ✦ Quant: TheBloke/loyal-piano-m7-AWQ ✦ Intended to be a roleplay-focused model with some smarts and good long-context recall

Updated 18 runs

A fine-tuned SDXL LoRA trained on images of stealth planes

Updated 33 runs

Notus-7b-v1 model

Updated 74 runs

Real-ESRGAN Upscale with AI Face Correction

Updated 9.3K runs