IS Net Anime
IS-Net-Anime is a deep learning model designed to provide interactive image segmentation capabilities. The model allows users to refine segmentation masks through user interactions, making it highly effective for...
Modellquelle
- Art
- Other
- Dateigröße
- 168 MB
- Version
- vRevision 99b14ab
- Aktualisiert
- 20. Okt. 2026
- Downloads
- 117
- Quelle
- Hugging Face
Quellenbeschreibung
IS-Net-Anime
Model Description
IS-Net-Anime is a deep learning model designed to provide interactive image segmentation capabilities. The model allows users to refine segmentation masks through user interactions, making it highly effective for tasks that require precise and detailed segmentation results.
Usage
Perform mask generation with BritishWerewolf/IS-Net-Anime.
Example
import { AutoModel, AutoProcessor, RawImage } from '@huggingface/transformers';
const img_url = 'https://huggingface.co/ybelkada/segment-anything/resolve/main/assets/car.png';
const image = await RawImage.read(img_url);
const processor = await AutoProcessor.from_pretrained('BritishWerewolf/IS-Net-Anime');
const processed = await processor(image);
const model = await AutoModel.from_pretrained('BritishWerewolf/IS-Net-Anime', {
dtype: 'fp32',
});
const output = await model({ input: processed.pixel_values });
// {
// mask: Tensor {
// dims: [ 1, 1024, 1024 ],
// type: 'uint8',
// data: Uint8Array(1048576) [ ... ],
// size: 1048576
// }
// }
Inference
To use the model for inference, you can follow the example provided above. The AutoProcessor and AutoModel classes from the transformers library make it easy to load the model and processor.
Credits
rembgfor the ONNX model.- The authors of the original IS-Net-Anime model can be credited at https://github.com/SkyTNT/anime-segmentation.
Licence
This model is licensed under the Apache License 2.0 to match the original IS-Net-Anime model.
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 20. Okt.
Modellartefakte
1 Artefakt
Modellartefakte
1 ArtefaktQuellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- library_name: transformers pipeline_tag: image-segmentation tags: - isnet - dis - anime - image-segmentation - mask-generation - transformers.js - vision - background-removal - portrait-matting license: apache-2.0 language: - en --- # IS-Net-Anime ## Model Description IS-Net-Anime is a deep learning model designed to provide interactive image segmentation capabilities. The model allows users to refine segmentation masks through user interactions, making it highly effective for tasks that require precise and detailed segmentation results. ## Usage Perform mask generation with `BritishWerewolf/IS-Net-Anime`. ### Example ```javascript import { AutoModel, AutoProcessor, RawImage } from '@huggingface/transformers'; const img_url = 'https://huggingface.co/ybelkada/segment-anything/resolve/main/assets/car.png'; const image = await RawImage.read(img_url); const processor = await AutoProcessor.from_pretrained('BritishWerewolf/IS-Net-Anime'); const processed = await processor(image); const model = await AutoModel.from_pretrained('BritishWerewolf/IS-Net-Anime', { dtype: 'fp32', }); const output = await model({ input: processed.pixel_values }); // { // mask: Tensor { // dims: [ 1, 1024, 1024 ], // type: 'uint8', // data: Uint8Array(1048576) [ ... ], // size: 1048576 // } // } ``` ### Inference To use the model for inference, you can follow the example provided above. The `AutoProcessor` and `AutoModel` classes from the `transformers` library make it easy to load the model and processor. ## Credits * [`rembg`](https://github.com/danielgatis/rembg) for the ONNX model. * The authors of the original IS-Net-Anime model can be credited at https://github.com/SkyTNT/anime-segmentation. ## Licence This model is licensed under the Apache License 2.0 to match the original IS-Net-Anime model.
Source context: 117 downloads · 3 likes · Pipeline image-segmentation · Library transformers · Repo BritishWerewolf/IS-Net-Anime
Source context: 34 downloads · 3 likes · Pipeline image-segmentation · Library transformers · Repo BritishWerewolf/IS-Net-Anime
