A text-to-image model based on the Stable Diffusion XL architecture,擅长生成高度逼真的图像，特别在人脸和手部细节处理上表现出色。

Computer VisionDiffusersEnglish

A Stable Diffusion model fine-tuned on epic images of spaceships and space stations, capable of generating high-quality images of space machinery and complex mechanical structures.

Computer VisionDiffusers

LLaVAction is a multimodal large language model for action recognition, based on the Qwen2 language model, trained on the EPIC-KITCHENS-100-MQA dataset.

MultimodalTransformersEnglish

Realistic Vision V5.1 is a text-to-image generation model based on Stable Diffusion XL, specifically designed to generate realistic photographic-grade images. This model has high application value in the field of image creation and can generate high-quality realistic-style images based on text descriptions.

MultimodalDiffusersEnglish

Realistic Vision V6.0 B1 is a text-to-image generation model based on Stable Diffusion XL, specializing in photorealistic and cinematic imagery.

Computer VisionDiffusersEnglish

A high-quality photo LoRA suitable for the SDXL model, capable of generating realistic images based on specific trigger words.

Computer VisionDiffusers

epiCRealism XL vXI-aBEAST is a text-to-image generation model based on Stable Diffusion XL, focusing on generating photorealistic images, especially female portraits and realistic photography works.

Computer VisionDiffusers

Captain Violet is a 12B-parameter merged model, created by combining Epiculous/Violet_Twilight-v0.2 and Nitral-AI/Captain_BMO-12B using the mergekit tool, supporting text generation tasks.

Natural Language ProcessingTransformersEnglish

A LoRA model based on FLUX.1-dev, focused on generating epic realistic style images, currently in training phase

Computer VisionDiffusers

Violet_Twilight-v0.2 is a SLERP-merged model of Azure_Dusk-v0.2 and Crimson_Dawn-v0.2, supporting multilingual text generation tasks.

Natural Language ProcessingGgufMultiple Languages

Violet_Twilight-v0.2 is a SLERP merged model of Azure_Dusk-v0.2 and Crimson_Dawn-v0.2, supporting multilingual text generation tasks.

Natural Language ProcessingSafetensorsMultiple Languages

A Sanskrit-to-English translation model fine-tuned from M2M100, trained on the Itihasa dataset containing translations of Sanskrit epics.

Natural Language ProcessingTransformersMultiple Languages

EpicRealism XL is a hyper-realistic text-to-image model, specializing in generating high-quality, detail-rich portraits and scene images.

Computer VisionDiffusers

An image generation model based on Stable Diffusion technology, focusing on producing highly realistic images

Computer VisionDiffusers

Crunchy-onion is an instruction-tuned model obtained by fine-tuning the Mixtral base model on datasets such as LimaRP, theory of mind, and Gnosis. It performs excellently under specific instruction formats. This model is trained using 4-bit QLoRA technology and finally merged into Mixtral Instruct, achieving the best results in the Alpaca Instruct format.

Natural Language ProcessingTransformers

This is a LoRA model based on Stable Diffusion XL, specifically designed for generating images with an epic sense of composition.

Computer VisionDiffusersEnglish

epiCRealism - Natural Sin RC1 VAE is a text-to-image generation model specializing in hyper-realistic style images, particularly excelling in creating high-detail, cinematic lighting effect portraits.

Computer VisionDiffusers

A text-to-image generation model capable of generating girl images with a surreal and realistic effect, suitable for various scenarios such as artistic creation and wallpaper design.

Computer VisionDiffusers

epicRealism v3 is an AI model focused on generating surrealistic images, capable of creating highly realistic and artistic portraits and scenes.

Computer VisionDiffusers

epiCRealism is a text-to-image generation model based on stable diffusion technology, specializing in producing highly realistic, photo-quality images.

Computer VisionDiffusersEnglish