Все модели
Полный список отсортирован по популярности на Replicate.
araby.ai oneshot video faceswap
RunDiffusion FX Photorealistic model, developed by RunDiffusion.
A low cost and fast version of Hailuo 02. Generate 6s and 10s videos in 512p
Realistic Vision v5.0 with VAE
Convert PDF to markdown + JSON quickly with high accuracy
A 40 billion parameter language model trained to follow human instructions.
This a pruna optimised version of the flux 1.dev model.
Realistic Vision v5.0 Inpainting
Run Wan2.1 14b or 1.3b with a lora
Interior remodelling, keeps windows, ceilings, and doors. Uses a depth controlnet weighted to ignore existing furniture.
live portrait with audio
A fine-tuned SDXL lora based on the Barbie movie
Intelligent image scaling to 4x resolution
Quickly generate smooth 5s or 8s videos at 540p, 720p or 1080p
Classification of music approachability and engagement
F5-TTS, the new state-of-the-art in open source voice cloning
BakLLaVA-1 is a Mistral 7B base augmented with the LLaVA 1.5 architecture
Remove eyeglasses and shadows from photo
A large-scale text-to-image generation model based on latent diffusion, developed by the Kuaishou Kolors team
The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate SDXL images with an image prompt
Use Runway's Stable-diffusion inpainting model to create an infinite loop video
SDXL Fine tuned on sketchnote style images. Prompt Prefix: a sketchnote photo of TOK
lmsys/vicuna-13b-v1.3
Generate 768px images from text using CompVis `retrieval-augmented-diffusion`
Segment Anything 2 (SAM2) by Meta - Automatic mask generation
Fast Segment Anything
Mistral-7B-v0.1 fine tuned for chat with the Dolphin dataset (an open-source implementation of Microsoft's Orca)
Use one or two face images to create AI avatars
Seed-X-PPO-7B by ByteDance-Seed, a powerful series of open-source multilingual translation language models
Public SDXL model trained on the style of Studio Ghibli
Adding semantic labels for segment anything
Removes the watermark from Sora 2 videos using a trained model and IOpaint
Generate 5s and 9s 720p videos
Google's Gemma2 9b instruct model
Generate videos using xAI's Grok Imagine Video model
Enhance Stable Diffusion prompt.
Run inpainting with Flux, compatible with Canny ControlNet, LoRAs and HyperFlux_8step
Real-ESRGAN with optional face correction and adjustable upscale (for larger images)
stable-diffusion with v1-5 checkpoint
3D artworks on Stable Diffusion via Dreambooth
Change the aspect ratio of any video up to 30 seconds long, outputs will be 720p
Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
A speech-to-text model that uses GPT-4o to transcribe audio
The Pastel Model with highres upscale
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.
A unified Text-to-Speech demo featuring three powerful modes: Voice, Clone and Design