Explore

I want to…

Enhance videos

Models that enhance videos with super-resolution, sound effects, motion capture and other useful production effects.

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

I have enjoyed watching "How to Train You Dragon", and I was specifically a big fan of Toothless. A unique, yet special Dragon, so I thought about generating more images of (him or it ? I dunno rlly...)

Updated 12 runs

A Llama-3.2-11B pretrained model, fine-tuned for content safety classification

Updated 4 runs

Updated 6 runs

Updated 64 runs

Updated 11 runs

Updated 16 runs

Image generation, Added: inpaint_strength loras_custom_urls

Updated 238.6K runs

sound separation with demucs

Updated 26.3K runs

Updated 9 runs

Updated 22 runs

Updated 35 runs

GPU accelerated replay renderer / video data clipper for comma.ai connect's openpilot route data. SEE README.

Updated 3.3K runs

FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models

Updated 36 runs

Updated 1 run

A SOTA for background removal - Bria v2.0

Updated 822 runs

Updated 3 runs

Updated 7 runs

Updated 20 runs

Updated 30 runs

Updated 29 runs

Updated 6 runs

Updated 19 runs

Flux fine-tuned on the trolley problem

Updated 71 runs

Updated 21 runs

A Llama-3.1-8B pretrained model, fine-tuned for content safety classification

Updated 22 runs

A 7B parameter Llama 2-based input-output safeguard model

Updated 8 runs

Image inpainting with flux

Updated 5 runs

A 12 billion parameter rectified flow transformer capable of generating images from text descriptions

Updated 6.8M runs

Updated 40 runs

Latest model in the Qwen family for chatting with video and image models

Updated 12 runs

Updated 21 runs

LTX-Video is the first DiT-based video generation model capable of generating high-quality videos in real-time. It produces 24 FPS videos at a 768x512 resolution faster than they can be watched.

Updated 16.8K runs

IA Model of Vinicius JR with Real Madrid Jersey

Updated 25 runs

Updated 104 runs

Remove backgrounds from images.

Updated 51K runs

The fastest image generation model tailored for local development and personal use

Updated 167.6M runs

Updated 83 runs

Updated 70 runs

Hunyuan-Video LoRA Explorer

Updated 124 runs

Updated 26 runs

Run any ComfyUI workflow on an A100. Guide: https://github.com/fofr/cog-comfyui

Updated 6.4K runs

Run any ComfyUI workflow. Guide: https://github.com/fofr/cog-comfyui

Updated 1.1M runs

SDXL Canny controlnet with LoRA support.

Updated 252.1K runs

Granite-3.1-8B-Instruct is a lightweight and open-source 8B parameter model is designed to excel in instruction following tasks such as summarization, problem-solving, text translation, reasoning, code tasks, function-calling, and more.

Updated 13.3K runs

Granite-3.1-2B-Instruct is a lightweight and open-source 2B parameter model designed to excel in instruction following tasks such as summarization, problem-solving, text translation, reasoning, code tasks, function-calling, and more.

Updated 22 runs

Fast Hunyuan Video by Hao AI Lab

Updated 94 runs

Flux fine-tuned on art of ruin

Updated 109 runs

Flux fine tuned on the 14 black paintings by Goya

Updated 373 runs

Flux fine-tuned on the art of William Blake

Updated 230 runs