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

Change the fps of a video without changing its length or speed

Updated 82 runs

Portrait animation using a driving video source

Updated 60.7K runs

Efficient Portrait Animation with Stitching and Retargeting Control

Updated 1.2K runs

Kolors is a SOTA base image model for high quality image generation

Updated 1.2K runs

Updated 13 runs

Updated 83 runs

Updated 24 runs

The API automatically detects objects in an input image and returns their positional and mask information.

Updated 4K runs

Convert images to anime style

Updated 225.5K runs

Create music for your content

Updated 200.7K runs

Updated 374 runs

Mama ママ 2.0 Shinsei Galverse Anime-themed text-to-image model

Updated 1.9K runs

InternLM2.5 has open-sourced a 7 billion parameter base model and a chat model tailored for practical scenarios.

Updated 49 runs

Updated 99 runs

Create videos from illustrated input images

Updated 37K runs

Updated 18 runs

Phi-3-Mini-4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets

Updated 95.3K runs

Qwen2 57 billion parameter language model from Alibaba Cloud, fine tuned for chat completions

Updated 1.1K runs

SDXL fine-tune based on images of birds primarily from the British Library free archive

Updated 17 runs

Generate clay style images based on prompts or images

Updated 369 runs

GLM-4V is a multimodal model released by Tsinghua University that is competitive with GPT-4o and establishes a new SOTA on several benchmarks, including OCR.

Updated 66.3K runs

Convert speech in audio to text w/ `tiny`, `small`, `base`, and `large-v3` models

Updated 61 runs

Dolphin-2.9 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling

Updated 244 runs

Extended video synthesis model that generates 128 frames

Updated 197 runs

Image generation, Inpaint Strength, loras custom_urls and enhancer.

Updated 403 runs

Updated 33 runs

Updated 55 runs

Updated 19 runs

Hermes 2 Pro is an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house

Updated 141 runs

Best Open-Source Model for Function Calling

Updated 25 runs

Updated 31 runs

Hermes-2 Θ (Theta) is the first experimental merged model released by Nous Research

Updated 15 runs

Hermes 2 Pro is an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house

Updated 1.7K runs

Speech to speech with any RVC v2 trained AI voice

Updated 167.9K runs

hello world

Updated 44 runs

Google's Gemma2 27b instruct model

Updated 1.8K runs

AuraSR: GAN-based Super-Resolution for real-world

Updated 1.7K runs

Google's Gemma2 9b instruct model

Updated 3.7K runs

Model

Updated 409 runs

A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

Updated 763 runs

Model that generates Cartoon like characters

Updated 738 runs

Stable Diffusion 3 with Differential Diffusion inpainting (experimental)

Updated 263 runs

Fork of https://replicate.com/schananas/grounded_sam that uses OwlV2 instead of Grounding Dino

Updated 544 runs

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

Updated 35.3K runs

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

Updated 28.1K runs

Updated 461 runs

Qwen 2: A 7 billion parameter language model from Alibaba Cloud, fine tuned for chat completions

Updated 1.6K runs

Qwen 2: A 1.5 billion parameter language model from Alibaba Cloud, fine tuned for chat completions

Updated 201 runs

A novel speech model for insane prosody.

Updated 280 runs

Qwen 2: A 0.5 billion parameter language model from Alibaba Cloud, fine tuned for chat completions

Updated 179 runs