Все модели
Полный список отсортирован по популярности на Replicate.
Omnilingual ASR 1B by Meta (Unofficial) - Automatic speech recognition supporting 1,693 languages with balanced accuracy and speed. Best general-purpose choice for professional transcription services.
A fine-tuned FLUX.1 model
Create images of Amelie's traveling dwarf. Simply write a location and include the trigger word 'ADWARF' to generate a Polaroid-style photo
Embedding generation using microsoft's xtremedistil-l6-h384-uncased model
Demucs v4 API
yuan2.0-2b-mars是源2.0-2B模型的2024年3月版本，源2.0 是浪潮信息发布的新一代基础语言大模型。我们开源了全部的3个模型源2.0-102B，源2.0-51B和源2.0-2B。并且我们提供了预训练，微调，推理服务的相关脚本，以供研发人员做进一步的开发。源2.0是在源1.0的基础上，利用更多样的高质量预训练数据和指令微调数据集，令模型在语义、数学、推理、代码、知识等不同方面具备更强的理解能力。
A LoRA style based on illustrated buildings from the Simpsons
Template Project for Running Fast Video Effects all on the GPU with fast GPU encoding and Decoding
Model similar to famous Armenian actor Frunzik Mkrtchyan
Hibiki: High-Fidelity Simultaneous Speech-To-Speech Translation
dolly-v2-12b， just for testing