Все модели
Полный список отсортирован по популярности на Replicate.
flux-latentpop features vibrant backgrounds with grungy limited screenprinting color goodness.
SDXL Finetuned on Zine-Style Portraits
Agentic image model optimized for robust, high-precision generations supporting font control
generate pixel art sprite sheets from four different angles with Stable-diffusion
Highly Accurate Dichotomous Image Segmentation （ECCV 2022）
Accelerated inference for HunyuanVideo with high resolution (1280x720), a state-of-the-art text-to-video generation model capable of creating high-quality videos with realistic motion from text descriptions
FlashFace: Human Image Personalization with High-fidelity Identity Preservation
PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding
Nougat: Neural Optical Understanding for Academic Documents
Fork of https://replicate.com/schananas/grounded_sam that uses OwlV2 instead of Grounding Dino
Realistic Vision V3.0 with VAE
Sentiment Analysis with Texts
Generates pokemon sprites from prompt
Generate retro videogame art using text.
GTA5 Artwork Diffusion via Dreambooth
Convert image or video of your face to anime
A fine-tuned FLUX.1 model. Use trigger word "EINSTEIN". Created with ReFlux (https://reflux.replicate.dev).
Realism photo with RealVisXl v4.0 ( Realistic Vision with Stable Diffusion XL )
An enhanced version of sd-interior-design, featuring improved diffusion model
SDXL fine-tuned on The Shining
Alibaba Wan 2.6 text to video generation model
Upscaler and detailer for a selected area
Wan 2.1 I2V (14B) 480p with CausVid LoRA
Fast and High-Quality Text-to-video Generation
VEED Fabric 1.0 is an image-to-video API that turns any image into a talking video
Segmind Stable Diffusion Model (SSD-1B) img2img
End-to-End Document Image Enhancement Transformer
Zero-shot speech synthesizer for text-to-speech and voice conversion
Pencil XL v2 Model (Text2Img, Img2Img and Inpainting)
An SDXL fine-tune for solid color images
This model can detect clothing using a custom state of the art clothing segmentation algorithm.
Lucid Sonic Dreams syncs GAN-generated visuals to music
Next Scene – “Next beat” cinematic edits that keep subject identity while steering to the next camera move via the Next Scene LoRA
Use stable diffusion and aesthetic CLIP embeddings to guide boring outputs to be more aesthetically pleasing.
Clip-Guided Diffusion Model for Image Generation
Qwen 2: A 7 billion parameter language model from Alibaba Cloud, fine tuned for chat completions
Kosmos-G: Generating Images in Context with Multimodal Large Language Models
Generate a collection of logos based on your text input. Use longer and more detailed inputs for better results. The first time it takes a few minutes to load the model. Subsequent generations are much faster.
Translate videos into over 150 languages
high-resolution piano transcription system: detects piano notes from audio
T5 model fine tuned on GPT-3.5 generated paraphrase corpus of 6.3 million unique sentences.
Virtual fitting of clothes
Animation Studio on Stable Diffusion via Dreambooth
Hotshot XL using SDXL for generating one second clips of high quality! Running on a40 Made by the greats at hotshot.co and brought to you by your friends at FullJourney! Thanks to LucaTaco for the MVP!
The API automatically detects objects in an input image and returns their positional and mask information.