leoxs22/manga-panel-detector-yolo26n
object-detection model by leoxs22
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
A lightweight YOLO26-nano model fine-tuned on Manga109-s for detecting panels and text bubbles in manga pages. Designed for on-device Android inference via TFLite/LiteRT. Use mangapaneldetectorint8.tflite with the TensorFlow Lite interpreter or Google's LiteRT runtime. These weights are a fine-tune of Ultralytics YOLO26, which Ultralytics distributes under the GNU Affero General Public License v3.0. Ultralytics' position is that models trained or fine-tuned from their weights and code fall under AGPL-3.0 as well, so this model is released under AGPL-3.0. In practice, this means: Earlier versions of this page listed the model as Apache 2.0. That label was incorrect, because I did not have the rights to grant it. If you adopted the model under that assumption, please review your project against the terms above. I'm not a lawyer, and whether…
Read the full model card ↗ · Preview checked 2026-10-01T06:41:26.839Z
Inside the original model card — Document outline
- Manga panel & text detector (YOLO26-nano)
- Performance
- INT8 TFLite (2.71 MB)
- Quantization impact (FP32 vs INT8)
- Training curves
- Model details
- Files
- Usage
- Python (ultralytics)
- Android (TFLite / LiteRT)
- Training
- License
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: agpl-3.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
leoxs22/manga-panel-detector-yolo26n is a object-detection model repository published by leoxs22 on Hugging Face. The source reports the ultralytics library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- object-detection
- Library
- ultralytics
- Recent downloads (30 days)
- 1,435
- Cumulative likes
- 16
- Hugging Face trending score
- 1
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- agpl-3.0
- Access
- Not gated by Hugging Face
- Created
- 2026-03-30T11:37:53.000Z
- Last modified
- 2026-09-24T20:55:13.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Ultralytics/YOLO26
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-01T06:41:23.286Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
mudler/locate-anything.cpp-gguf
microsoft/table-transformer-structure-recognition
PaddlePaddle/PP-DocLayoutV3_safetensors