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

Updated 2 runs

Updated 17 runs

Updated 26 runs

Updated 34 runs

Updated 41 runs

Updated 73 runs

Updated 71 runs

Updated 99 runs

Updated 76 runs

Updated 86 runs

Updated 36 runs

Updated 17 runs

Updated 72 runs

Updated 300 runs

Updated 252 runs

Updated 2 runs

Updated 38 runs

Updated 8 runs

Updated 49 runs

Updated 4 runs

idk what this is

Updated 12 runs

Updated 14 runs

mingaeul character appearance

Updated 18 runs

Updated 18 runs

Dreamlike Diffusion Model for Splurge Art

Updated 1.7K runs

A fine-tuned Flux model

Updated 798 runs

Finetuned on this collection of midjourney images https://monoliths.uncut.network/

Updated 93 runs

A fine-tuned FLUX.1 model

Updated 36 runs

A fine-tuned FLUX.1 model

Updated 60 runs

From Sketch to Reality: Transforming Outlines into Lifelike Images

Updated 35.2K runs

Updated 15 runs

Updated 61 runs

Fast FLUX DEV -> Flux Controlnet Canny, Controlnet Depth , Controlnet Line Art, Controlnet Upscaler - You can use just one controlnet or All - LORAs: HyperFlex LoRA , Add Details LoRA , Realism LoRA

Updated 25.6K runs

Updated 316 runs

baby transformer for blog post

Updated 26 runs

staging testing

Updated 237 runs

An experiment: a fine-tuned FLUX model for UI design generation

Updated 339 runs

Document translation with contextual integrity.

Updated 53 runs

interior ai

Updated 98 runs

Updated 46 runs

Updated 133 runs

Updated 189 runs

Updated 16 runs

Updated 49 runs

Align text to audio with exact word timings. All characters supported!

Updated 11.4K runs

Projection module trained to add vision capabilties to Llama 3 using SigLIP

Updated 5.3K runs

Updated 92 runs

Updated 31 runs

Remodels interior

Updated 291 runs

Recraft V3 SVG (code-named red_panda) is a text-to-image model with the ability to generate high quality SVG images including logotypes, and icons. The model supports a wide list of styles.

Updated 19.6K runs