Все модели

Полный список отсортирован по популярности на Replicate.

mcai/dreamshaper-v6

Generate a new image given any input text with DreamShaper V6

423 382 запусков
ibm-granite/granite-3.0-2b-instruct

Granite-3.0-2B-Instruct is a lightweight and open-source 2B parameter model designed to excel in instruction following tasks such as summarization, problem-solving, text translation, reasoning, code tasks, function-calling, and more.

420 296 запусков
black-forest-labs/flux-canny-pro

Professional edge-guided image generation. Control structure and composition using Canny edge detection

415 857 запусков
spuuntries/flatdolphinmaid-8x7b-gguf

Undi95's FlatDolphinMaid 8x7B Mixtral Merge, GGUF Q5_K_M quantized by TheBloke.

415 758 запусков
lucataco/illusion-diffusion-hq

Monster Labs QrCode ControlNet on top of SD Realistic Vision v5.1

410 736 запусков
openai/gpt-image-1-mini

A cost-efficient version of GPT Image 1

409 386 запусков
andreasjansson/illusion

Monster Labs' control_v1p_sd15_qrcode_monster ControlNet on top of SD 1.5

409 115 запусков
google/veo-3.1-fast

New and improved version of Veo 3 Fast, with higher-fidelity video, context-aware audio and last frame support

404 094 запусков
catacolabs/sdxl-ad-inpaint

Product advertising image generator using SDXL

401 484 запусков
openai/o4-mini

OpenAI's fast, lightweight reasoning model

400 918 запусков
lucataco/snowflake-arctic-embed-l

snowflake-arctic-embed is a suite of text embedding models that focuses on creating high-quality retrieval models optimized for performance

398 507 запусков
lucataco/sdxl-lcm

Latent Consistency Model (LCM): SDXL, distills the original model into a version that requires fewer steps (4 to 8 instead of the original 25 to 50)

398 051 запусков
vetkastar/fooocus

Image generation, Added: inpaint_strength loras_custom_urls

397 168 запусков
zsxkib/flux-dev-inpainting

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

391 410 запусков
aisha-ai-official/wai-nsfw-illustrious-v11

391 047 запусков
tommoore515/material_stable_diffusion

Stable diffusion fork for generating tileable outputs

390 205 запусков
lucataco/gfpgan

Practical face restoration algorithm for *old photos* or *AI-generated faces* (for larger images)

389 131 запусков
fofr/audio-to-waveform

Create a waveform video from audio

384 119 запусков
recraft-ai/recraft-remove-background

Automated background removal for images. Tuned for AI-generated content, product photos, portraits, and design workflows

382 742 запусков
ideogram-ai/ideogram-v2a-turbo

Like Ideogram v2 turbo, but now faster and cheaper

381 665 запусков
chenxwh/depth-anything-v2

Depth estimation with faster inference speed, fewer parameters, and higher depth accuracy.

381 324 запусков
microsoft/omniparser-v2

OmniParser is a screen parsing tool to convert general GUI screen to structured elements.

380 482 запусков
rafaelgalle/whisper-diarization-advanced

Ultra-fast, customizable speech-to-text and speaker diarization for noisy, multi-speaker audio. Includes advanced noise reduction, stereo channel support, and flexible audio preprocessing—ideal for call centers, meetings, and podcasts.

377 795 запусков
ideogram-ai/ideogram-v3-balanced

Balance speed, quality and cost. Ideogram v3 creates images with stunning realism, creative designs, and consistent styles

377 346 запусков
openai/gpt-5-structured

GPT-5 with support for structured outputs, web search and custom tools

374 019 запусков
lambdal/stable-diffusion-image-variation

Image Variations with Stable Diffusion

370 159 запусков
recraft-ai/recraft-v3-svg

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.

366 809 запусков
sesamo-srl/bge-reranker-v2-m3

Newest reranker model from BAAI (https://huggingface.co/BAAI/bge-reranker-v2-m3). FP16 inference enabled. Normalize param available

366 322 запусков
meta/llama-guard-3-8b

A Llama-3.1-8B pretrained model, fine-tuned for content safety classification

362 411 запусков
meta/llama-2-70b

Base version of Llama 2, a 70 billion parameter language model from Meta.

362 272 запусков
zust-ai/supir

361 358 запусков
konieshadow/fooocus-api-anime

Third party Fooocus replicate model with preset 'anime'

357 673 запусков
lucataco/qwen2-vl-7b-instruct

Latest model in the Qwen family for chatting with video and image models

356 851 запусков
cjwbw/anything-v3.0

high-quality, highly detailed anime style stable-diffusion

354 023 запусков
nandycc/sdxl-app-icons

Fine tuned to generate awesome app icons, by aistartupkit.com

353 024 запусков
zedge/live-portrait

351 340 запусков
microsoft/phi-3-mini-128k-instruct

Phi-3-Mini-128K-Instruct is a 3.8 billion-parameter, lightweight, state-of-the-art open model trained using the Phi-3 datasets

350 351 запусков
bria/expand-image

Bria Expand expands images beyond their borders in high quality. Resizing the image by generating new pixels to expand to the desired aspect ratio. Trained exclusively on licensed data for safe and risk-free commercial use

350 076 запусков
google/veo-3.1

New and improved version of Veo 3, with higher-fidelity video, context-aware audio, reference image and last frame support

349 831 запусков
laion-ai/erlich

Generate a logo using text.

349 742 запусков
mcai/absolutebeauty-v1.0-img2img

Generate a new image from an input image with AbsoluteReality v1.0

348 542 запусков
aisha-ai-official/nsfw-flux-dev

341 584 запусков
pvitoria/chromagan

An Adversarial Approach for Picture Colorization

337 816 запусков
jagilley/controlnet-normal

Modify images using normal maps

330 817 запусков
minimax/hailuo-02

Hailuo 2 is a text-to-video and image-to-video model that can make 6s or 10s videos at 768p (standard) or 1080p (pro). It excels at real world physics.

330 231 запусков
lucataco/animate-diff

Animate Your Personalized Text-to-Image Diffusion Models

328 587 запусков
prompthero/dreamshaper

Generate a new image given any input text with Dreamshaper v7

326 108 запусков
fofr/pulid-base

Use a face to make images. Uses SDXL fine-tuned checkpoints.

325 516 запусков
mtg/effnet-discogs

An EfficientNet for music style classification by 400 styles from the Discogs taxonomy

324 933 запусков
aisha-ai-official/illust3relustion

324 206 запусков