Все модели

Полный список отсортирован по популярности на Replicate.

iliketoasters/flux-miniature-people

Flux lora, use "miniature man", "miniature woman" or "miniature people" to trigger generation

369 запусков
oxanaon/oxana

369 запусков
debesu/a-photo-of-ashu

368 запусков
grey-hound432/fast-image-quality-compressor

A simple and efficient image compression model that reduces file size while maintaining image quality. Designed to boot quickly and deliver results in under a second.

367 запусков
lucataco/sdxl-lcm-loras

POC of SDXL-LCM LoRA combined with a Replicate LoRA for 4 second inference time

367 запусков
sergiosevilla95/ser

367 запусков
anotherjesse/sdxl-lcm-testing

366 запусков
bfirsh/aidungeon

Colab version of AI Dungeon

366 запусков
zeke/tarot-flux

This model is not great. Check out this other one that's better: https://replicate.com/apolinario/flux-tarot-v1

365 запусков
brockmesarich/thumbnailfinal

364 запусков
impetusdesign/rqi-txc-itp

364 запусков
leonardoa2/cult-contemplazione

364 запусков
lucataco/animate-diff-sdxl-lcm

Animate Your Personalized Text-to-Image Diffusion Models with SDXL and LCM

364 запусков
menghanxia/reversiblehalftoning

Deep Halftoning with Reversible Binary Pattern

364 запусков
swk23/padmelive

364 запусков
cjwbw/magicoder

LLMs with open-source code snippets for generating low-bias and high-quality instruction data for code.

363 запусков
farplane-ai/harry-clarke-illustration-lora

363 запусков
tenetnets/apexgenex

363 запусков
andreasjansson/flux-monkey-island

362 запусков
man5hatki/povar

362 запусков
bigrj100/yogagirl

Beautiful yoga girl model for all, enjoy

361 запусков
cirosan910/alfajor

360 запусков
cjwbw/cutie

Video Object Segmentation, combined with SAM and ProPainter

360 запусков
cyber42/remedios_varo

SDXL fine tuned on a set of paintings of Remedios Varo. Activate the fine tuning with the prefix: "In the style of RemediosVaro, ..."! Helps to include the negative prompt: "broken, disfigured, dismembered people".

360 запусков
lucataco/hermes-2-pro-llama-3-70b

Hermes 2 Pro is an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house

360 запусков
magpai-app/cog-ffprobe

Get the width, height, and duration in seconds from a video

360 запусков
cbx1/sam-vit-h

The Segment Anything Model (SAM) is a powerful and versatile image segmentation model. It leverages a "foundation model" approach, meaning it can be used for various segmentation tasks without needing to be specifically trained for each one.

359 запусков
cjwbw/instructcv

Instruction tuned text-to-image diffusion models as vision generalists

359 запусков
venkr/whisperx-diarization

Whisper-Large-V2 + Pyannote 3.0 diarization via WhisperX

359 запусков
0xdino/cyberrealistic-pony-semireal-v36

358 запусков
adams38/red_page_ai

358 запусков
nucksftw13/kim3

Kim Kardashian with black hair and wide hips

358 запусков
yuguochencuc/db-aiat

Dual-branch Attention-In-Attention Transformer for single-channel speech enhancement

358 запусков
zeg06/stefbo

357 запусков
cjwbw/blipdiffusion

Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing

356 запусков
cjwbw/stable-diffusion-aesthetic-gradients

Stable Diffusion with Aesthetic Gradients

356 запусков
lucataco/blueprint

An SDXL fine-tune based on blueprints

356 запусков
matsuitran/sdxl-anime-schoolboy

Stable Diffusion XL fine-tunned in the theme of Anime Schoolboy

356 запусков
jichengdu/got-ocr-2

Towards OCR-2.0 via a Unified End-to-end Model

355 запусков
aisha-ai-official/real-dream-pony-v15

354 запусков
martintmv-git/sdxl-cinematic

SDXL Fine-tune on cinematic shots

354 запусков
ostris/flex.1-alpha

Flex.1 alpha is a pre-trained base 8 billion parameter rectified flow transformer capable of generating images from text descriptions

354 запусков
park683/han

354 запусков
vcollos/vitor

354 запусков
deepfates/hunyuan-arcane

Hunyuan-Video model finetuned on Arcane (2021). Trigger word is "RCN". Use "A video in the style of RCN, RCN" at the beginning of your prompt for best results.

353 запусков
jan890/flux_dev_ascii_art

This AI ASCII Image Generator converts text prompts into detailed ASCII art images. Just include the trigger word "ASCII" in your text prompt, and the model, fine-tuned on Flux1 Dev, will generate an ASCII art representation of your description. The model

353 запусков
krisdoan/gb2045g

353 запусков
madaguru/lauramdg

353 запусков
klassenmedia/moris

351 запусков
gauravburande/flux-tesla-optimus-robot-lora

Flux lora for Tesla Optimus robot, use "OPTIMAUSI" to trigger generations

350 запусков