Explore

I want to…

Enhance videos

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

Restore images

Models that improve or restore images by deblurring, colorization, and removing noise

Make 3D stuff

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

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

Hunyuan-Video LoRA Explorer + Trainer

Updated 4.1K runs

Takes audio (mp3) and a "source-of-truth" audio transcript (string) as input and returns precise timestamps.

Updated 16 runs

Updated 0 runs

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

Updated 1.1M runs

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

Updated 7.4K runs

Updated 0 runs

Professional inpainting and outpainting model with state-of-the-art performance. Edit or extend images with natural, seamless results.

Updated 86.7K runs

Meta Segment Anything model for a click point

Updated 8 runs

Updated 4 runs

Updated 0 runs

Updated 35 runs

Updated 39 runs

Updated 30 runs

A Great Photographer

Updated 77 runs

SVFR: A Unified Framework for Generalized Video Face Restoration

Updated 72 runs

a personal model to play around

Updated 32 runs

Updated 21 runs

Updated 185 runs

State-of-the-art human detection and tracking system integrated with REID

Updated 12 runs

This is an optimised version of the flux schnell model from black forest labs with the pruna tool. We achieve a ~3x speedup over the original model with minimal quality loss.

Updated 61 runs

Updated 30 runs

Updated 14 runs

HunyuanVideo finetune of an AI avatar from Heygen

Updated 11 runs

Updated 26 runs

This model generates pose variation of a cartoon character. It preserves the cartoon identity. Use this model to augment training dataset for any cartoon character created through AI. The augmented dataset can be used to train a LoRA model.

Updated 110 runs

Image generation, Added: inpaint_strength loras_custom_urls

Updated 250.9K runs

Simple tool to merge together separate video snippets

Updated 13 runs

flux_schnell model img2img inference

Updated 7.3K runs

Updated 11 runs

HunyuanVideo finetune of an AI avatar from Heygen

Updated 12 runs

Updated 121 runs

allenai/OLMo-2-1124-13B-Instruct, text generation model

Updated 30 runs

Updated 163 runs

Updated 13 runs

Updated 82 runs

Updated 17 runs

HunyuanVideo finetune of Walt Disney's: 1928 Steamboat Willie

Updated 48 runs

Updated 21 runs

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

Updated 30.3K runs

2025 fork of closed Coqui XTTS-v2: Multilingual Text To Speech Voice Clone

Updated 211 runs

Visage de femme a mettre en scene

Updated 205 runs

Updated 119 runs

A powerful 3D asset generation model

Updated 12.5K runs

Cog implementation of LTX video from its diffusers pipeline

Updated 58 runs

Cog implementation of LTX image to video from its diffusers pipeline

Updated 21 runs

flux dev

Updated 53.7K runs

HunyuanVideo finetune of an AI Avatar from Heygen

Updated 47 runs

This models allow changing the strength of the Redux image prompt, which allows the text prompt to have a stronger effect. It is particularly useful at taking content from the provided image and applying style or editing changes from the prompt.

Updated 122 runs

Change the strength of the prompt to enable editing style and content. Recommendation: keep the seed constant and tune the strength.

Updated 63 runs

Hunyuan fine-tuned on Cyberpunk 2077 photorealistic graphics mods, use CYB77 keyword

Updated 39 runs