Qwen-Image-Edit-Cosplay LoRA is an anime character dressing migration model fine-tuned based on the Qwen-Image-Edit-2509 image editing model. It focuses on accurately migrating the hairstyles, clothing, and decorative props of anime characters to real human images while maintaining the facial features of the original person.

Computer VisionDiffusers

A 3B parameter instruction fine-tuned model based on Qwen2.5 architecture, optimized for training speed using Unsloth and Huggingface TRL library

Natural Language ProcessingTransformersEnglish

Haitian Creole speech recognition model fine-tuned based on OpenAI Whisper-medium, focusing on high-accuracy transcription

Audio ProcessingTransformersOther

This is a Haitian Creole text-to-speech model, fine-tuned based on jsbeaudry/haitian_creole.

Audio ProcessingTransformers

This is a sentence-transformers model fine-tuned from Alibaba-NLP/gte-multilingual-base, supporting Vietnamese for tasks like semantic text similarity.

Natural Language ProcessingSafetensorsOther

A LoRa model for generating high-definition images of 2000s singer Avril Lavigne, especially suitable for recreating her signature blonde hair and black eyeliner look.

Computer VisionDiffusersOther

An image classification model based on Google's Vision Transformer (ViT) architecture, specifically designed to identify five hairstyle types (curly, dreadlocks, twists, straight, wavy) from facial images with 93% accuracy.

Computer VisionSafetensors

This is a LoRA model fine-tuned based on the FLUX.1-dev base model, specifically designed for generating cat images with unique hairstyle styles.

Computer VisionDiffusers

A style LoRA model trained on 25 photos of Hailee Steinfeld, capable of generating images in a specific style without trigger words

Computer VisionDiffusers

StoryMaker is a personalized solution capable of maintaining consistency in facial features, clothing, hairstyles, and body characteristics across multi-character scenarios, designed for creating stories composed of a series of images.

MultimodalDiffusersEnglish

EXLMR is an extended version of XLM-R that supports new languages by expanding the tokenizer vocabulary to mitigate out-of-vocabulary issues, specifically optimized for low-resource Ethiopian languages.

Natural Language ProcessingTransformersOther

Experimental text-to-speech model trained on five Hakka dialects (Dabu, Hailu, Raoping, Sixian, Zhao'an)

Audio ProcessingTransformersOther

A Whisper-based speech recognition model optimized for Haitian Creole, featuring high-accuracy speech-to-text conversion

Audio ProcessingTransformersOther

This is an image classification model based on PyTorch framework, capable of recognizing five different hair color categories.

Computer VisionTransformers

Haitian Creole text-to-speech model developed by Meta, part of the Massively Multilingual Speech (MMS) project

Audio ProcessingTransformers

This model is a fine-tuned version of whisper-small-cv11-french, optimized for Haitian Creole speech recognition

Audio ProcessingTransformers

A Haitian Creole text-to-speech model fine-tuned on the cmu_haitian dataset based on microsoft/speecht5_tts

Audio ProcessingTransformersOther

A Haitian Creole text-to-speech model fine-tuned based on the SpeechT5 architecture, trained using Carnegie Mellon University's Haitian language dataset

Audio ProcessingTransformersOther

MoeDiffusion++ is a text-to-image model specialized in generating anime characters with black hair and twin tails, optimized for facial expressions and style control through the fusion of multiple base models.

Computer VisionDiffusersMultiple Languages

This is an image classification model based on the PyTorch framework, capable of accurately identifying and classifying hair length (long or short).

Computer VisionTransformers