MiaoshouAI
commited on
Commit
•
6ecbf9c
1
Parent(s):
79ed3c5
Update README.md
Browse files
README.md
CHANGED
@@ -16,13 +16,13 @@ You won't get annoying captions like "This is image is about a girl..." or
|
|
16 |
|
17 |
## Features:
|
18 |
* Describes image in much detail when using \<MORE_DETAILED_CAPTION\> instruction.
|
19 |
-
<img style="width:
|
20 |
* When using \<DETAILED_CAPTION\> instruction, it creates a structured caption with infomation on subject's position and also reads the text from the image, which can be super useful when recreate a scene.
|
21 |
-
<img style="width:
|
22 |
* Memory efficient compare to other models! This is a really light weight caption model that allows you to use a little more than 1G of VRAM and produce lightening fast and high quality image captions.
|
23 |
-
<img style="width:
|
24 |
* Designed to handle image captions for Flux model for both T5XXL CLIP and CLIP_L, the Miaoshou Tagger new node called "Flux CLIP Text Encode" which eliminates the need to run two separate tagger tools for caption creation. You can easily populate both CLIPs in a single generation, significantly boosting speed when working with Flux models.
|
25 |
-
<img style="width:
|
26 |
|
27 |
## Instruction prompt:
|
28 |
\<GENERATE_TAGS\> generate prompt as danbooru style tags<br>
|
|
|
16 |
|
17 |
## Features:
|
18 |
* Describes image in much detail when using \<MORE_DETAILED_CAPTION\> instruction.
|
19 |
+
<img style="width:100%; hight:100%" src="https://msdn.miaoshouai.com/miaoshou/bo/2024-09-05_12-40-34.png" />
|
20 |
* When using \<DETAILED_CAPTION\> instruction, it creates a structured caption with infomation on subject's position and also reads the text from the image, which can be super useful when recreate a scene.
|
21 |
+
<img style="width:100%; hight:100%" src="https://msdn.miaoshouai.com/miaoshou/bo/2024-09-05_13-07-54.png" />
|
22 |
* Memory efficient compare to other models! This is a really light weight caption model that allows you to use a little more than 1G of VRAM and produce lightening fast and high quality image captions.
|
23 |
+
<img style="width:100%; hight:100%" src="https://msdn.miaoshouai.com/miaoshou/bo/2024-09-05_12-56-39.png" />
|
24 |
* Designed to handle image captions for Flux model for both T5XXL CLIP and CLIP_L, the Miaoshou Tagger new node called "Flux CLIP Text Encode" which eliminates the need to run two separate tagger tools for caption creation. You can easily populate both CLIPs in a single generation, significantly boosting speed when working with Flux models.
|
25 |
+
<img style="width:100%; hight:100%" src="https://msdn.miaoshouai.com/miaoshou/bo/2024-09-05_14-11-02.png" />
|
26 |
|
27 |
## Instruction prompt:
|
28 |
\<GENERATE_TAGS\> generate prompt as danbooru style tags<br>
|