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

Manmaru mix v3.0

Updated 695 runs

Source: allenai/digital-socrates-13b ✦ Quant: TheBloke/digital-socrates-13B-AWQ ✦ Digital Socrates is an open-source, automatic explanation-critiquing model

Updated 17 runs

Source: Unbabel/TowerInstruct-7B-v0.1 ✦ Quant: TheBloke/TowerInstruct-7B-v0.1-AWQ ✦ This model is trained to handle several translation-related tasks, such as general machine translation, gramatical error correction, and paraphrase generation

Updated 186 runs

Improving the Stability of Diffusion Models for Content Consistent Super-Resolution

Updated 3.2K runs

ProteusV0.1 uses OpenDalleV1.1 as a base and further refines prompt adherence and stylistic capabilities to a measurable degree

Updated 6.6K runs

Great image quality, good old SDXL with a new and improved Tile refiner.

Updated 768 runs

Audio-based Lip Synchronization for Talking Head Video

Updated 26K runs

SDVN10-Anime

Updated 330 runs

Updated 199 runs

SDXL Trained on blue jeans

Updated 250 runs

赤羽全域のモデルです!最新版なのでこちらをお使いください!

Updated 1K runs

Improved background remover 2.0 - GroundingDino + SAM + Inpainting SDXL + Controlnet Canny

Updated 205 runs

Automatic Speech Recognition with Word-level Timestamps & Diarization

Updated 3.2K runs

Towards Photo-Realistic Image Colorization via Dual Decoders

Updated 154.8K runs

Source: Neuronovo/neuronovo-7B-v0.3 ✦ Quant: TheBloke/neuronovo-7B-v0.3-AWQ ✦ Neuronovo/neuronovo-7B-v0.3 model represents an advanced and fine-tuned version of a large language model, initially based on CultriX/MistralTrix-v1.

Updated 37 runs

Yuan2.0 is a new generation LLM developed by IEIT System, enhanced the model's understanding of semantics, mathematics, reasoning, code, knowledge, and other aspects.

Updated 384 runs

SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution

Updated 48.3K runs

Pheme generates a variety of conversational voices in 16 kHz for phone-call applications

Updated 403 runs

Updated 69 runs

make meow emojis!

Updated 53 runs

90s anime

Updated 21.3K runs

Updated 183 runs

Generates game icons, For full use: appiconlab.com

Updated 214.3K runs

multilingual-e5-large: A multi-language text embedding model

Updated 10.5M runs

multilingual-e5-base: A multi-language text embedding model

Updated 5 runs

multilingual-e5-small: A multi-language text embedding model

Updated 11 runs

Updated 40 runs

Gerador de música para games condicionado a emoção feito para a disciplina de Residência em IA do Bacharelado em Inteligência Artificial-UFG

Updated 179 runs

Amused is a lightweight text to image model based off of the muse architecture. Amused is particularly useful in applications that require a lightweight and fast model such as generating many images quickly at once.

Updated 192 runs

Updated 279 runs

Super-fast, 0.6s per image. LCM with img2img, large batching and canny controlnet

Updated 1.2M runs

SDXL fine-tuned on energy drink designs

Updated 1.6K runs

Updated 2.3K runs

Cheaper model SwinIR: Image Restoration Using Swin Transformer (analogue of the popular model: jingyunliang/swinir)

Updated 839 runs

A SOTA Nous Research finetune of 200k Yi-34B fine tuned on the Capybara dataset.

Updated 1.9K runs

SDXL fine-tuned on photos of freshly inked tattoos

Updated 35.8K runs

Video toolkit – convert, make GIFs, extract audio

Updated 4.2K runs

Make your video talk anything

Updated 1.2K runs

Updated 176 runs

Diffusion Models for Image Morphing

Updated 996 runs

A 34 billion parameter Llama tuned for coding and conversation

Updated 145.7K runs

A 7 billion parameter Llama tuned for coding and conversation

Updated 61.4K runs

Updated 304 runs

(Academic and Non-commercial use only) Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization

Updated 38.5K runs

Updated 295 runs

Lob RealVis XL

Updated 59.4K runs

whisper-large-v3, incredibly fast, with video transcription

Updated 109.7K runs

RESEARCH/NON-COMMERCIAL USE ONLY: diffusion-based audio-driven expressive talking head generation

Updated 986 runs

SDXL LoRA finetuned on diamond watches

Updated 52 runs

SDXL LoRA finetuned on Vermeer paintings

Updated 88 runs