Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,21 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model:
|
4 |
+
- Minthy/ToriiGate-v0.3
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
tags:
|
8 |
+
- multimodal
|
9 |
+
- vision
|
10 |
+
- image-text-to-text
|
11 |
+
---
|
12 |
+
|
13 |
+
|
14 |
+
**Torii-Gate-v0.3-nf4** is a bnb nf4 quant of [ToriiGate-v0.3](https://huggingface.co/Minthy/ToriiGate-v0.3) which is based on [Idefics3](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3).
|
15 |
+
|
16 |
+
It is designed for captioning of anime arts and aims to achieve a good understading for a very wide range of images, including single/multiple characters, simple or complex scenes, comic or manga, various interactions and lots of highly cultural concepts.
|
17 |
+
Using booru-tags grounding it can give detailed descriptions with very high accuracy. It can handle NSFW pretty well, being one of the best small/medium-sized open source models at the time of release.
|
18 |
+
|
19 |
+
For batch processing you can use [ide-cap-chan](https://github.com/2dameneko/ide-cap-chan)
|
20 |
+
|
21 |
+
All other features are inherited from the parent model.
|