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 "in the style of FNTSYRCH" to trigger

Updated 62 runs

Updated 32 runs

Updated 15 runs

flux.1 'plastic3d' style lora

Updated 467 runs

Generate detailed mobile app user interfaces (UIs) using prefix “MOBIUI containing..” in 4-15 steps.

Updated 431 runs

Flux finetuned for black and white line art.

Updated 784 runs

Updated 61 runs

Updated 33 runs

FLUX.1 [dev] trained on the Replicate goo

Updated 1.3K runs

Join the Granite community where you can find numerous recipe workbooks to help you get started with a wide variety of use cases using this model. https://github.com/ibm-granite-community

Updated 531.4K runs

Updated 63 runs

The first Bruce model.

Updated 8 runs

Creates Outputs in the Style of Backyard Sports Characters

Updated 67 runs

Turn text from the law in Spanish to structured data to feed support building a knowledge graph

Updated 2 runs

Updated 71 runs

Updated 49 runs

Flux lora, use "spitting image caricature" to trigger image generation

Updated 362 runs

Flux lora, trigger image generation with "west pier"

Updated 68 runs

Flux LoRA trained on generated images of random shapes

Updated 555 runs

Random rectangles, ellipses, lines, in random colors

Updated 83 runs

flux.1 'celestial pastel' lora

Updated 305 runs

Omni-Zero: A diffusion pipeline for zero-shot stylized portrait creation.

Updated 148.2K runs

Edward Hopper(realist painter) inspired Flux Lora

Updated 197 runs

图文识别

Updated 70 runs

Flux LoRa trained on Secret of Monkey Island

Updated 414 runs

Test model

Updated 3 runs

视频识别自动分割场景

Updated 16 runs

Updated 79 runs

提取视频中的图片

Updated 4 runs

提取视频中的音频

Updated 12 runs

Generate 16:9 Thumbnails. Use prefix - `Thumbnail in the style of TOK`

Updated 1.5K runs

Join the Granite community where you can find numerous recipe workbooks to help you get started with a wide variety of use cases using this model. https://github.com/ibm-granite-community

Updated 106.1K runs

Cinematic Flux LoRA: Use "r3dcma" in your prompt to trigger this LoRA model.

Updated 7K runs

Flux LoRA, use 'GHIBSKY style' to trigger generation, creates serene and enchanting landscapes with vibrant, surreal skies and intricate, Ghibli-inspired elements reminiscent of the atmospheric beauty found in Makoto Shinkai's works

Updated 34.8K runs

Updated 2.6K runs

A flux lora for panoramas, use 21:9 and "HDRI panoramic view of TOK" to trigger image generation

Updated 704 runs

Flux Lora inspired by Kodak Portra 800

Updated 143 runs

Fine tuned Lora Japanese style reference. Defaults to traditional red, grey and blue.

Updated 305 runs

Updated 15 runs

Take photos in the style of a Lomography camera

Updated 2.9K runs

epic xkcd comics

Updated 7K runs

Run FLUX.1 with lora and controlnet

Updated 586 runs

Flux lora inspired by early 2000s animation movies, use 1.2 guidance

Updated 232 runs

🎨 Fill in masked parts of images with FLUX.1-dev 🖌️

Updated 139.6K runs

Make pictures of an AI character named 0_1.webp

Updated 1.5K runs

Cubiq's ComfyUI InstantID node running `instantid_basic.json` example

Updated 1.1K runs

Flux lora, use "Y2K" to trigger image generation

Updated 378 runs

Updated 23 runs

Retro style Flux Lora

Updated 894 runs

Generates hand-drawn sketchnotes with great detail. Prompt Prefix: “A sketchnote in the style of TOK”

Updated 4.5K runs