98 models match the criteria

This model is based on the transformers library, with no specific details provided.

Depth Anything V2 is currently the most powerful monocular depth estimation model, trained on 595,000 synthetically annotated images and over 62 million real unlabeled images, featuring fine details and robustness.

Depth Anything V2 is currently the most powerful monocular depth estimation model, trained on a large amount of synthetic and real images, providing fine depth details and high robustness.

This model is released under the MIT License, specific details are currently unknown.

Depth Anything V2 is currently the most powerful Monocular Depth Estimation (MDE) model, trained on 595,000 synthetically annotated images and over 62 million real unlabeled images, offering finer details and stronger robustness.

Depth Anything V2 is currently the most powerful monocular depth estimation model, trained on large-scale synthetic and real images. Compared to V1, it captures finer details and is more robust.

DepthCrafter is a model capable of generating temporally coherent long depth sequences for open-world videos with fine details, without requiring additional information such as camera poses or optical flow.

Depth Anything V2 is currently the most powerful monocular depth estimation model, trained on 595,000 synthetically annotated images and over 62 million real unlabeled images, offering finer details and stronger robustness.

This is a fine-tuned object detection model for the fashion domain, based on the YOLOS architecture, capable of recognizing and localizing fashion items and their details.

A high-resolution LoRA adapter specifically designed for Animagine XL 2.0 to enhance the quality and details of anime-style images.

A ControlNet Tile model based on the SDXL framework for enhancing or altering original image details, compatible with WebUI and ComfyUI

InternVideo2.5 is a video multimodal large language model enhanced by Long and Rich Context (LRC) modeling, built upon InternVL2.5. It significantly improves existing MLLM models by enhancing the ability to perceive fine-grained details and capture long-term temporal structures.

I-JEPA is a self-supervised learning method that predicts representations of other parts of an image from partial representations, without relying on manual data transformations or filling in pixel-level details.

This model is released under the MIT license, specific details are currently unknown.

A LoRA model customized based on the FLUX.1-dev model, specifically designed for generating fantasy-style wizard and witch images, significantly enhancing image details.

This model is released under the MIT License, with specific details currently unknown.

A hyper-realistic model utilizing LoRA fine-tuning technology, capable of generating high-quality images with realistic textures, lighting, and intricate details.

InternVideo2.5 is a video multimodal large language model (MLLM) built upon InternVL2.5, enhanced with Long and Rich Context (LRC) modeling, capable of perceiving fine-grained details and capturing long-term temporal structures.

A high-quality stable diffusion model capable of generating realistic images from text descriptions, especially excelling in portrait rendering and complex details.

A model capable of generating lively anime-style illustrations with special effect details, especially suitable for fantasy themes.

This model is released under the MIT license, with specific details currently unknown.

This model is released under the Creative Commons Attribution-NonCommercial 4.0 International License. For specific details, please refer to the model page.

A cutting-edge large-scale image generation model, excelling in producing images with astonishing clarity, precision, and intricate details, particularly suited for high-resolution imagery and realistic scene generation.

This model presents fantasy characters with exaggerated proportions and rounded lines, featuring rich 3D rendering details that blend cute cartoon designs with realistic lighting and textures.

A detail adjustment tool specifically designed for SDXL, enhancing or reducing image generation details through LoRA model

Anything3.0 is an overfitted model, excelling in generating character images and specific details, capable of producing high-quality images even with suboptimal prompts.

A super-realistic image generation model based on LoRA fine-tuning technology, focusing on producing high-quality images with lifelike textures and intricate details.

The model card information is incomplete and cannot provide specific details

A Stable Diffusion model focused on generating highly realistic pony images, with special emphasis on facial details, skin textures, and lighting effects.

SkyCaptioner-V1 is a model specifically designed for generating high-quality structured descriptions of video data. By integrating specialized sub-expert models, multimodal large language models, and manual annotations, it addresses the limitations of general description models in capturing professional film details.

Open-source model under Apache-2.0 license (specific details unavailable)

add-detail-xl is a detail adjustment model for SDXL. It can increase or decrease image details by adjusting the weight, bringing more flexibility to image generation.

A detail adjustment tool specifically designed for SDXL, enhancing or simplifying image details through LoRA technology

A video multimodal large language model enhanced by Long and Rich Context (LRC) modeling, improving existing MLLMs by enhancing the perception of fine-grained details and capturing long-term temporal structures

This model is released under the MIT license, specific details are currently unavailable.

A Stable Diffusion XL-based text-to-image generation model focused on producing high-quality, semi-realistic female portraits with photorealistic details and rich visual expression.

This model is released under the Apache-2.0 license, with specific details currently unknown.

A LoRA adapter designed for Animagine XL 2.0, adding rich Art Nouveau-style details and decorative elements to anime images

A video multimodal large language model using a slow-fast architecture, balancing temporal resolution and spatial details, supporting 64-frame video understanding

A fine-tuned version based on the BERT base model, specific use case and training data details are currently unknown

This model is released under the MIT License; further details need to be supplemented.

PRM is a novel large-scale reconstruction model based on photometric stereo vision, capable of reconstructing high-quality mesh models with fine local details.