Все модели
Полный список отсортирован по популярности на Replicate.
Model
Monocular relative depth estimation
shoreline refinement for small island satellite derived shorelines
NeureaLenin by soon®: a V. I. Lenin SDXL fine-tuning; use "LEN" token in prompts!
An SDXL fine-tune on the Tesla Roadster 2.0
Cogified implementation of OminiControl
cineball from an image
speaking on big stage with legacy life in background and people in audience
Hunyuan-Video model finetuned on RRR (2022). Trigger word is "RRR". Use "A video in the style of RRR, RRR" at the beginning of your prompt for best results.
Use the HUNT word to invoke the style: "A man walking on a field, HUNT style"
Kolors: Effective Training of Diffusion Model for Photorealistic Text-to-Image Synthesis
A unified omni-modal model that can simultaneously receive inputs such as images, audio, text, and video and directly generate coherent text and speech
ModernBERT-base is a modernized bidirectional encoder-only Transformer model (BERT-style) pre-trained on 2 trillion tokens of English and code data
Tiled inference implementation of PLKSR
A fine-tuned FLUX.1 model
Base version of Mamba 2.8B Slim Pyjama, a 2.8 billion parameter state space language model
remove background for retailer product images
Detect and classify speech bubbles in manga images