Все модели

Полный список отсортирован по популярности на Replicate.

arabyai-replicate/roop_face_swap

araby.ai oneshot video faceswap

41 983 запусков
fermatresearch/photorealistic-fx

RunDiffusion FX Photorealistic model, developed by RunDiffusion.

41 710 запусков
minimax/hailuo-02-fast

A low cost and fast version of Hailuo 02. Generate 6s and 10s videos in 512p

41 589 запусков
lucataco/realistic-vision-v5

Realistic Vision v5.0 with VAE

41 526 запусков
datalab-to/marker

Convert PDF to markdown + JSON quickly with high accuracy

41 511 запусков
joehoover/falcon-40b-instruct

A 40 billion parameter language model trained to follow human instructions.

41 434 запусков
prunaai/flux.1-juiced

This a pruna optimised version of the flux 1.dev model.

41 340 запусков
lucataco/realistic-vision-v5-inpainting

Realistic Vision v5.0 Inpainting

41 210 запусков
wan-video/wan2.1-with-lora

Run Wan2.1 14b or 1.3b with a lora

41 196 запусков
jschoormans/comfyui-interior-remodel

Interior remodelling, keeps windows, ceilings, and doors. Uses a depth controlnet weighted to ignore existing furniture.

40 987 запусков
zf-kbot/live-portrait

live portrait with audio

40 873 запусков
fofr/sdxl-barbie

A fine-tuned SDXL lora based on the Barbie movie

40 857 запусков
raoumer/srrescgan

Intelligent image scaling to 4x resolution

40 741 запусков
meta/llama-guard-4-12b

40 668 запусков
pixverse/pixverse-v4

Quickly generate smooth 5s or 8s videos at 540p, 720p or 1080p

40 569 запусков
mtg/music-approachability-engagement

Classification of music approachability and engagement

40 252 запусков
x-lance/f5-tts

F5-TTS, the new state-of-the-art in open source voice cloning

40 063 запусков
lucataco/bakllava

BakLLaVA-1 is a Mistral 7B base augmented with the LLaVA 1.5 architecture

39 824 запусков
enhancerandroid02/flix_q8_i2v_gamma

39 416 запусков
storymy/take-off-eyeglasses

Remove eyeglasses and shadows from photo

39 166 запусков
fofr/kolors

A large-scale text-to-image generation model based on latent diffusion, developed by the Kuaishou Kolors team

38 880 запусков
lucataco/ip_adapter-sdxl-face

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate SDXL images with an image prompt

38 503 запусков
arielreplicate/stable_diffusion_infinite_zoom

Use Runway's Stable-diffusion inpainting model to create an infinite loop video

38 469 запусков
justmalhar/sxdl-sketchnotes

SDXL Fine tuned on sketchnote style images. Prompt Prefix: a sketchnote photo of TOK

38 428 запусков
lucataco/vicuna-13b-v1.3

lmsys/vicuna-13b-v1.3

38 415 запусков
afiaka87/retrieval-augmented-diffusion

Generate 768px images from text using CompVis `retrieval-augmented-diffusion`

38 394 запусков
aihilums/sehatsanjha

37 772 запусков
lucataco/segment-anything-2

Segment Anything 2 (SAM2) by Meta - Automatic mask generation

37 457 запусков
casia-iva-lab/fastsam

Fast Segment Anything

37 446 запусков
lucataco/dolphin-2.2.1-mistral-7b

Mistral-7B-v0.1 fine tuned for chat with the Dolphin dataset (an open-source implementation of Microsoft's Orca)

37 390 запусков
easel/ai-avatars

Use one or two face images to create AI avatars

37 176 запусков
lucataco/seed-x-ppo

Seed-X-PPO-7B by ByteDance-Seed, a powerful series of open-source multilingual translation language models

36 818 запусков
karanchawla/studio-ghibli

Public SDXL model trained on the style of Studio Ghibli

36 654 запусков
cjwbw/semantic-segment-anything

Adding semantic labels for segment anything

36 618 запусков
uglyrobot/sora2-watermark-remover

Removes the watermark from Sora 2 videos using a trained model and IOpaint

36 479 запусков
luma/ray-2-720p

Generate 5s and 9s 720p videos

36 468 запусков
google-deepmind/gemma2-9b-it

Google's Gemma2 9b instruct model

36 431 запусков
xai/grok-imagine-video

Generate videos using xAI's Grok Imagine Video model

36 361 запусков
gan-tu/flux-dev-ai-signature

36 306 запусков
2feet6inches/cog-prompt-parrot

Enhance Stable Diffusion prompt.

36 121 запусков
fermatresearch/flux-controlnet-inpaint

Run inpainting with Flux, compatible with Canny ControlNet, LoRAs and HyperFlux_8step

36 078 запусков
lucataco/real-esrgan

Real-ESRGAN with optional face correction and adjustable upscale (for larger images)

35 946 запусков
cjwbw/stable-diffusion-v1-5

stable-diffusion with v1-5 checkpoint

35 906 запусков
nitrosocke/redshift-diffusion

3D artworks on Stable Diffusion via Dreambooth

35 906 запусков
luma/reframe-video

Change the aspect ratio of any video up to 30 seconds long, outputs will be 720p

35 868 запусков
bytedance/sa2va-8b-image

Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

35 721 запусков
openai/gpt-4o-transcribe

A speech-to-text model that uses GPT-4o to transcribe audio

35 504 запусков
elct9620/pastel-mix

The Pastel Model with highres upscale

35 490 запусков
wavespeedai/wan-2.1-t2v-720p

Accelerated inference for Wan 2.1 14B text to video with high resolution, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.

35 456 запусков
qwen/qwen3-tts

A unified Text-to-Speech demo featuring three powerful modes: Voice, Clone and Design

35 435 запусков