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 85 runs

test-world

Updated 5 runs

Updated 11 runs

Hermes-2 Θ (Theta) is the first experimental merged model released by Nous Research, in collaboration with Charles Goddard at Arcee, the team behind MergeKit.

Updated 28.7K runs

Mobius: Redefining State-of-the-Art in Debiased Diffusion Models

Updated 62 runs

Updated 57 runs

Updated 63 runs

Updated 132 runs

Diffusion-based Visual Foundation Model for High-quality Dense Prediction

Updated 99 runs

Updated 129 runs

Updated 14 runs

Updated 36 runs

FLUX.1-Dev Multi LoRA Explorer

Updated 481K runs

FLUX.1-Dev LoRA Explorer

Updated 2.1M runs

A Sabine Wren Lora for Flux1

Updated 240 runs

FLUX dev fine-tuned on screenshots from the game Baldur's Gate 3

Updated 260 runs

Flux LoRA Training Experiment - Training two people in one LoRA with two images

Updated 339 runs

Updated 39 runs

Flux finetune of Violeta - specific layer training

Updated 209 runs

This is a test version, more updates coming

Updated 143 runs

Updated 83 runs

Updated 40 runs

Updated 57 runs

Transcribes audio using Whisper Large V3 with precise word-level timestamps and confidence scores.

Updated 274 runs

Updated 112 runs

Generates subtitles from audio using whisperX (faster-whisper-large-v3)

Updated 97 runs

Type Niko to picture me in any situation

Updated 28 runs

Updated 274 runs

Updated 20 runs

Updated 14 runs

Updated 12 runs

Updated 21 runs

Updated 36 runs

Updated 83 runs

Imagine your own shoe style

Updated 39 runs

Updated 30 runs

Updated 43 runs

Updated 21 runs

A soon-to-be accelerated endpoint for multi-modal inference.

Updated 135 runs

Updated 91 runs

Updated 103 runs

Generates images of old books

Updated 14 runs

Updated 95 runs

Updated 19 runs

Updated 45 runs

Controlnet trained on black-forest-labs/FLUX.1-dev with lineart condition

Updated 196 runs

Updated 503 runs

Generate images in a CGA PC Game style

Updated 89 runs

The fastest image generation model tailored for local development and personal use

Updated 128.9M runs

A 12 billion parameter rectified flow transformer capable of generating images from text descriptions

Updated 4.9M runs