Explore

I want to…

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

Use FLUX fine-tunes

Browse the diverse range of fine-tunes the community has custom-trained on Replicate

Control image generation

Guide image generation with more than just text. Use edge detection, depth maps, and sketches to get the results you want.

Latest models

Updated 380 runs

Updated 12 runs

Updated 79 runs

Updated 34 runs

A SOTA for background removal - Bria v2.0

Updated 101 runs

Updated 4 runs

Updated 131 runs

High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training

Updated 99 runs

A fast image model with wide artistic range and resolutions up to 4096x4096

Updated 21K runs

Updated 29 runs

Updated 26 runs

Updated 20 runs

Updated 2.2K runs

Updated 28 runs

Remodels interior

Updated 474 runs

Updated 49 runs

Updated 203 runs

Moondream 0.5B, the world's smallest vision language model

Updated 13 runs

Updated 15 runs

The Qwen2.5-Coder-32B-Instruct is a state-of-the-art, open-source large language model (LLM). It is specifically designed for coding tasks and is part of the Qwen2.5-Coder series, featuring 32 billion parameters.

Updated 25 runs

Accelerated variant of Photon prioritizing speed while maintaining quality

Updated 1.3K runs

High-quality image generation model optimized for creative professional workflows and ultra-high fidelity outputs

Updated 1.8K runs

A state-of-the-art text-to-video generation model capable of creating high-quality videos with realistic motion from text descriptions

Updated 4.8K runs

Updated 34 runs

The Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out).

Updated 6 runs

Video Preprocessor for Mochi-1 Training

Updated 2 runs

Flux fine-tuned on weird old Victorian Xmas cards

Updated 164 runs

Generate 4s and 6s videos from a prompt or image

Updated 644 runs

https://civitai.com/models/317902

Updated 21.4K runs

Updated 58 runs

Updated 384 runs

Make realistic images of real people instantly

Updated 30 runs

Updated 64 runs

Updated 61 runs

trained on 25 images of one red orlinsky sculpture, the model DOES NOT WORK well

Updated 66 runs

Flux lora trained on photos of Neelesh Kumar

Updated 217 runs

Updated 39 runs

A version of flux-dev, a text to image model, that supports fast fine-tuned lora inference

Updated 14.3K runs

Updated 13 runs

flux.1-dev: hyper-sd 8 steps + instanx ip adataper + pulid + depth controlnet

Updated 145 runs

A version of mochi-1 (a text to video model) that supports fine-tuned lora inference

Updated 18 runs

The fastest image generation model tailored for fine-tuned use

Updated 4.6K runs

Updated 145 runs

Updated 31 runs

Let Vision Language Models Reason Step-by-Step

Updated 12 runs

Updated 70 runs

Updated 63 runs

Welcome to Danny K's World

Updated 217 runs

Mochi 1 preview is an open video generation model with high-fidelity motion and strong prompt adherence in preliminary evaluation

Updated 957 runs

Updated 37 runs