efficientnet-b4
Google基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗DISCOVER & COMPARE
探索 AI 模型 1529
efficientnet-b5
Google基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗efficientnet-b6
Google基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗efficientnet-b7
GoogleEfficientNet model trained on ImageNet-1k at resolution 600x600. It was introduced in the paper EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks by Mingxing Tan and Quoc V. Le, and first released in this repository. Disclaimer: The team releasing EfficientNet did not write a model card for this model so this model card has been written by the Hugging Face team. EfficientNet is a mobile friendly pure convolutional model (ConvNet) that proposes a new scaling method that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient.
译文排队中 · 当前显示来源原文
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗mobilenet_v1_0.75_192
GoogleMobileNet V1 model pre-trained on ImageNet-1k at resolution 192x192. It was introduced in MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications by Howard et al, and first released in this repository. Disclaimer: The team releasing MobileNet V1 did not write a model card for this model so this model card has been written by the Hugging Face team. > MobileNets are small, low-latency, low-power models parameterized to meet the resource constraints of a variety of use cases. They can be built upon for classification, detection, embeddings and segmentation similar to how other popular large scale models, such as Inception, are used. MobileNets can be run efficiently on mobile devices [...] MobileNets trade off between latency, size and accuracy while comparing favorably with popular models from the literature.
译文排队中 · 当前显示来源原文
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗mobilenet_v1_1.0_224
GoogleMobileNet V1 model pre-trained on ImageNet-1k at resolution 224x224. It was introduced in MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications by Howard et al, and first released in this repository. Disclaimer: The team releasing MobileNet V1 did not write a model card for this model so this model card has been written by the Hugging Face team. > MobileNets are small, low-latency, low-power models parameterized to meet the resource constraints of a variety of use cases. They can be built upon for classification, detection, embeddings and segmentation similar to how other popular large scale models, such as Inception, are used. MobileNets can be run efficiently on mobile devices [...] MobileNets trade off between latency, size and accuracy while comparing favorably with popular models from the literature.
译文排队中 · 当前显示来源原文
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗mobilenet_v2_0.35_96
Google基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗mobilenet_v2_0.75_160
Google基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗mobilenet_v2_1.0_224
GoogleMobileNet V2 model pre-trained on ImageNet-1k at resolution 224x224. It was introduced in MobileNetV2: Inverted Residuals and Linear Bottlenecks by Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen. It was first released in this repository. Disclaimer: The team releasing MobileNet V2 did not write a model card for this model so this model card has been written by the Hugging Face team. From the original README:
译文排队中 · 当前显示来源原文
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗mobilenet_v2_1.4_224
Google基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗path-foundation
Google基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗vit-base-patch16-384
GoogleVision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224, and fine-tuned on ImageNet 2012 (1 million images, 1,000 classes) at resolution 384x384. It was introduced in the paper An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale by Dosovitskiy et al. and first released in this repository. However, the weights were converted from the timm repository by Ross Wightman, who already converted the weights from JAX to PyTorch. Credits go to him. Disclaimer: The team releasing ViT did not write a model card for this model so this model card has been written by the Hugging Face team. The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a supervised fashion, namely ImageNet-21k, at a resolution of 224x224 pixels. Next, the model was fine-tuned on ImageNet (also referred to as ILSVRC2012), a dataset comprising 1 million images and 1,000 classes, at a higher resolution of 384x384.
译文排队中 · 当前显示来源原文
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗vit-base-patch32-384
GoogleVision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224, and fine-tuned on ImageNet 2012 (1 million images, 1,000 classes) at resolution 384x384. It was introduced in the paper An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale by Dosovitskiy et al. and first released in this repository. However, the weights were converted from the timm repository by Ross Wightman, who already converted the weights from JAX to PyTorch. Credits go to him. Disclaimer: The team releasing ViT did not write a model card for this model so this model card has been written by the Hugging Face team. The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a supervised fashion, namely ImageNet-21k, at a resolution of 224x224 pixels. Next, the model was fine-tuned on ImageNet (also referred to as ILSVRC2012), a dataset comprising 1 million images and 1,000 classes, at a higher resolution of 384x384.
译文排队中 · 当前显示来源原文
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗vit-hybrid-base-bit-384
Google基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗vit-large-patch16-224
GoogleVision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224, and fine-tuned on ImageNet 2012 (1 million images, 1,000 classes) at resolution 224x224. It was introduced in the paper An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale by Dosovitskiy et al. and first released in this repository. However, the weights were converted from the timm repository by Ross Wightman, who already converted the weights from JAX to PyTorch. Credits go to him. Disclaimer: The team releasing ViT did not write a model card for this model so this model card has been written by the Hugging Face team. The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a supervised fashion, namely ImageNet-21k, at a resolution of 224x224 pixels. Next, the model was fine-tuned on ImageNet (also referred to as ILSVRC2012), a dataset comprising 1 million images and 1,000 classes, at the same resolution, 224x224.
译文排队中 · 当前显示来源原文
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗vit-large-patch16-384
GoogleVision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224, and fine-tuned on ImageNet 2012 (1 million images, 1,000 classes) at resolution 384x384. It was introduced in the paper An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale by Dosovitskiy et al. and first released in this repository. However, the weights were converted from the timm repository by Ross Wightman, who already converted the weights from JAX to PyTorch. Credits go to him. Disclaimer: The team releasing ViT did not write a model card for this model so this model card has been written by the Hugging Face team. The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a supervised fashion, namely ImageNet-21k, at a resolution of 224x224 pixels. Next, the model was fine-tuned on ImageNet (also referred to as ILSVRC2012), a dataset comprising 1 million images and 1,000 classes, at a higher resolution of 384x384.
译文排队中 · 当前显示来源原文
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗vit-large-patch32-384
GoogleVision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224, and fine-tuned on ImageNet 2012 (1 million images, 1,000 classes) at resolution 384x384. It was introduced in the paper An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale by Dosovitskiy et al. and first released in this repository. However, the weights were converted from the timm repository by Ross Wightman, who already converted the weights from JAX to PyTorch. Credits go to him. Disclaimer: The team releasing ViT did not write a model card for this model so this model card has been written by the Hugging Face team. The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a supervised fashion, namely ImageNet-21k, at a resolution of 224x224 pixels. Next, the model was fine-tuned on ImageNet (also referred to as ILSVRC2012), a dataset comprising 1 million images and 1,000 classes, at a higher resolution of 384x384.
译文排队中 · 当前显示来源原文
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗sonocnn
habib-analyst基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗vit-base-nsfw-detector
hakl36This model is a fine-tuned version of vit-base-patch16-384 on around 25_000 images (drawings, photos...). It achieves the following results on the evaluation set: - Loss: 0.0937 - Accuracy: 0.9654 ** New [07/30] **: I created a new ViT model specifically to detect NSFW/SFW images for stable diffusion usage (read the disclaimer below for the reason): **AdamCodd/vit-nsfw-stable-diffusion**. **Disclaimer**: This model wasn't made with generative images in mind! There is no generated image in the dataset used here, and it performs significantly worse on generative images, which will require another ViT model specifically trained on generative images. Here are the model's actual scores for generative images to give you an idea: - Loss: 0.3682 (↑ 292.95%) - Accuracy: 0.8600 (↓ 10.91%) - F1: 0.8654 - AUC: 0.9376 (↓ 5.75%) - Precision: 0.8350 - Recall: 0.8980
译文排队中 · 当前显示来源原文
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Facial-expression-detection
HardlyHumans基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗vit-base-patch16-224-blur_vs_clean
harrytechiz基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗second-eye
harvinderbhullar> **Research prototype, not a medical device.** Not validated for clinical use. Do not use it to > diagnose or treat anyone. A small trainable image **state head** for CLM (Contrastive Language Models). Frozen `nvidia/C-RADIOv2-H` image features (the vision tower of NVIDIA Nemotron Nano 2 VL) go through this head into CLM's 512-d action space. There they are scored by `scale · cos` against CLM's frozen **action tower** (Qwen3-8B last-token pooling + the released CLM-v0.1-8B action head) embedding the answer options: Code, training and evaluation: https://github.com/HarvinderBhullar/second-eye/tree/hackathon (see `docs/VISION.md`).
译文排队中 · 当前显示来源原文
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗mahjong-models
HaseLab基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 图像→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗暂未找到匹配模型
可以调整厂商、分类或输入输出条件；新模型正持续收录。
COST EXPLORER
好模型，也要算好成本。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
1 M = 100 万 Token · 美元计价
仅比较同一渠道的基础文本 Token 报价
仅比较同一渠道的基础文本 Token 报价
使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照；不计缓存优惠、阶梯价、推理额外输出与税费，请以来源的当前报价为准。
MODEL HANDBOOK
读懂模型，再做选择
API 价格应该怎么比较？+
先区分输入、输出和缓存价格，再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费，不能直接与 Token 单价比较。
开放权重，就代表可以免费商用吗？+
不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。
排行榜第一，就是最适合我的模型吗？+
榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本，再选择模型。