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

Dreamshaper canny controlnet

Updated 226 runs

Updated 72 runs

Updated 73 runs

Updated 6 runs

Flux Lora for a colorful twist, use "tr1ppy style illustration" to trigger. See Readme for more prompts.

Updated 1.6K runs

Show a nice guy if you use the keyword Eugenito

Updated 6 runs

Flux lora, use "grainyr3tro style illustration" as trigger

Updated 50 runs

Updated 82 runs

Updated 9 runs

Flux finetune that is trained on Glitches generated by a Processing Script ( In Readme ), WIP.

Updated 951 runs

Updated 72 runs

Updated 51 runs

Generate photos like old school US National Park Posters

Updated 69 runs

Turn anything into an abstract fine art masterpiece 🎨

Updated 797 runs

The "newspaper illustration" model specializes in creating black-and-white, cartoon-style drawings reminiscent of classic newspaper illustrations.

Updated 7.6K runs

lora for 70s band aesthetics

Updated 142 runs

A fine-tuned FLUX.1 model v1.1

Updated 34 runs

Updated 203 runs

Updated 262 runs

Flux lora, trained on macro textures, use "MCROTX" to trigger image generation

Updated 559 runs

Updated 74 runs

Flux lora based on the original Myst video game

Updated 59 runs

Updated 13 runs

Flux lora of Alex Lawther, trained on 20 images. Trigger word:"lawther"

Updated 18 runs

Caption any images.

Updated 3.8K runs

Updated 64 runs

Flux version of FormFinder-XL - trained to create moody atmospheric images but is quite versatile to be mixed with other LoRAs to generate diverse styles with interesting architecture design shapes. As the name suggests: it will always tend to surprise yo

Updated 14.1K runs

Lora of myself

Updated 28 runs

A Flux fine-tune of https://replicate.com/zeke the real-life human. Use "ZIKI" in the prompt to activate the trained style.

Updated 1.8K runs

Updated 932 runs

fine tuned flux+lora model with my face

Updated 109 runs

Updated 62 runs

Updated 236 runs

Hyper FLUX 16-step by ByteDance

Updated 651.7K runs

Updated 63 runs

Updated 625 runs

Updated 49 runs

Hyper FLUX 8-step by ByteDance

Updated 2.8M runs

This will convert any video to anime

Updated 47 runs

Flux lora trained on Midjourney v3 outputs from 2022, use "a dream, in the style of MJV3" to trigger generation, also try increasing lora strength above 1

Updated 3.7K runs

A hand drawn sketch style LoRA

Updated 82 runs

Flux lora, use "1980s anime screengrab", "VHS quality", or "syntheticanime" to trigger image generation

Updated 344 runs

Flux lora, trained on the unique style and aesthetic of ghibli retro anime

Updated 2K runs

Updated 34 runs

Flux lora, use "GMOVEUS" to trigger movement MEME

Updated 48.9K runs

Updated 39 runs

Updated 62 runs

Updated 36 runs

Flux LoRA, use 'DIXIT' to trigger generation, creates images with the art style of the board game DIXIT.

Updated 165 runs

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

Updated 38 runs