Все модели
Полный список отсортирован по популярности на Replicate.
A fine-tuned SDXL LoRA trained on images of stealth planes
flux-1.dev
Quickly detect nudity, violence, hentai, porn and more NSFW content in images.
Fast Mochi by Hao AI Lab
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data
Stable Diffusion v2.1, running 100% in Rust.
Simple video chroma keying
Image super-resolution model based on SEESR, designed to reconstruct low-resolution images with sharper details and accurate colors.
CodeLlama 34B with embedding output
InternLM2.5 has open-sourced a 7 billion parameter base model and a chat model tailored for practical scenarios.
VeenaMAX is a high-performance, advanced Text-to-Speech API that converts text into natural-sounding speech with emotional intelligence and blazing-fast response times. It can speak English and Hindi - the most widely used languages in India. As a signifi
Global-Local Path Networks (GLPN) model trained on NYUv2 for Monocular Depth Estimation
A blazing-fast inference setup for Flux.1-dev with dynamic LoRA hotswapping.
The aesthetic combines cozy cottagecore and ironic humor, using bold outlines, vibrant colors, and halftone textures in a playful comic book style.
Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
this is a first model