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

Flux LoRA, use 'PRVDETC' to trigger generation, creates characters based on the art style of the board game Painter Detective.

Updated 38 runs

Updated 88 runs

Generate high quality videos from a prompt

Updated 1.4K runs

Updated 43 runs

Updated 182 runs

ControlNet for FLUX.1-dev model jointly released by InstantX and Shakker Labs

Updated 1.2K runs

Flux LoRA, trigger style with "in the style of TOK", Photographic images with a beautiful glow

Updated 1.4K runs

Testing versions of myself

Updated 2 runs

Updated 31 runs

Updated 63 runs

Updated 7 runs

Updated 39 runs

Updated 81 runs

Updated 16 runs

Demucs is an audio source separator created by Facebook Research.

Updated 347.5K runs

Flux lora, use the term "MNALSA" to trigger generation

Updated 2.5K runs

Updated 66 runs

Updated 20 runs

a public experiment with the AI generated figure of Paul Mittelrheintaler, a cool YouTuber in the middle Rhine Valley. Created by Marcus Schwarze

Updated 63 runs

Updated 8 runs

Flux finetune trained on Syd Mead concept art for Blade Runner

Updated 749 runs

Hayao Miyazaki watercolor sketch LoRA

Updated 130 runs

Updated 101 runs

Use "TOK" to trigger style, multiple angle portraits, with 90s and Y2K and throwback nostalgia

Updated 244 runs

InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output

Updated 34 runs

A LoRA for Flux.1 Dev to re-create really bad and trippy CGI from the 90s.

Updated 1.6K runs

Ganpati image generation model trained on all Ganapati in Pune, India

Updated 68 runs

Updated 117 runs

Updated 265 runs

A Fulx1.D based lora for gaoyuanyuan,trigger word "gyy"

Updated 45 runs

Updated 15 runs

Flux-dev inference & LoRa training

Updated 266 runs

Virtual try-on using Stable Diffusion and IP-Adapter

Updated 1.2K runs

replace background with Stable Diffusion and ControlNet

Updated 125.9K runs

outpaint with stable diffusion and ControlNet

Updated 18.5K runs

Flux.1 fine-tune on soviet-era controlrooms

Updated 56 runs

Best-in-class clothing virtual try on in the wild (non-commercial use only)

Updated 404.4K runs

Updated 109 runs

Flux lora by AggravatingScree7189, use "cyberpunk typeface" to trigger image generation

Updated 734 runs

run comfyui flow

Updated 15 runs

Flux lora, use "CNSTLL" to trigger

Updated 60.5K runs

Updated 57 runs

Updated 64 runs

Updated 118 runs

Flux LoRA: Use "m1st1c" in your prompt to trigger this LoRA model.

Updated 5.5K runs

Generates logograms in the style of the alien language from the 2016 sci-fi film "Arrival".

Updated 171 runs

Updated 218 runs

Mimicking the classic woodblock print. Use “in the style of TOK”

Updated 48 runs

Flux lora, use "in the style of FNTSYRCH" to trigger

Updated 62 runs