The theme of this LoRA is girly clothes with lots of frills, and designs that require a lot of effort to draw. Because this is the first edition, the tags are not well organized, and the material is mainly illustrations. For better learning, it would be good to add images of mannequins wearing the clothes and detailed close-up images. Also, I tried to use `LoraPlus`, but there are some points that I am not able to fully utilize.
Although I realize my learning is incomplete, I have made some progress and am now ready to publish the first edition.
-Network Rank : 16
-Learning rate : UNet 0.001 / Text Encoder 0.0001
-Scheduler : CosineAnnealingLR (T_max=860, eta_min=1e-7 )
Euphemism
The file name is goth-XLPony_009 because Cvitai will reject it if it is written in English, but the gothic elements are just a little hidden, and there are also a few landmine elements.
Lolita fashion has many subcategories, from the major Gothic Lolita to Sweet Lolita, Japanese Lolita, Chinese Lolita, and so on, so it's hard to keep up with them all.
I thought so.
When I was uploading a sample, Lolita fashion came up as a recommendation.
Civitai has come to forgive me
---
---
### ENG
This LoRA was created to alleviate the burden of managing a large number of images, utilizing some automation tools:
- [Script for improving images]( https://github.com/NEXTAltair/Lorayougazouwoiroiroirosurusukuriputo )
- [Script for refining tags]( https://github.com/NEXTAltair/genai-tag-db-tools )
The theme of this LoRA revolves around girly clothes adorned with frills and intricate designs that require significant drawing effort. The initial version lacks well-organized tags and is mainly based on illustration materials. To improve the model, including photos with mannequins and close-up images would be essential. Although I attempted to use LoraPlus, I couldn't fully leverage its potential.
While appreciating the imperfections, the model is reasonably complete for a first release.
---
### Training Parameters
Key Points
- Network Rank : 16
- Learning Rate : UNet 0.001 / Text Encoder 0.0001
- Scheduler : CosineAnnealingLR (T_max=860, eta_min=1e-7)
---
### Example Execution Command
---
Description
The theme of this LoRA is girly clothes with lots of frills, and designs that require a lot of effort to draw. Because this is the first edition, the tags are not well organized, and the material is mainly illustrations. For better learning, it would be good to add images of mannequins wearing the clothes and detailed close-up images. Also, I tried to use `LoraPlus`, but there are some points that I am not able to fully utilize.
Although I realize my learning is incomplete, I have made some progress and am now ready to publish the first edition.
-Network Rank : 16
-Learning rate : UNet 0.001 / Text Encoder 0.0001
-Scheduler : CosineAnnealingLR (T_max=860, eta_min=1e-7 )
Euphemism
The file name is goth-XLPony_009 because Cvitai will reject it if it is written in English, but the gothic elements are just a little hidden, and there are also a few landmine elements.
Lolita fashion has many subcategories, from the major Gothic Lolita to Sweet Lolita, Japanese Lolita, Chinese Lolita, and so on, so it's hard to keep up with them all.
I thought so.
When I was uploading a sample, Lolita fashion came up as a recommendation.
Civitai has come to forgive me
---
---
### ENG
This LoRA was created to alleviate the burden of managing a large number of images, utilizing some automation tools:
- [Script for improving images]( https://github.com/NEXTAltair/Lorayougazouwoiroiroirosurusukuriputo )
- [Script for refining tags]( https://github.com/NEXTAltair/genai-tag-db-tools )
The theme of this LoRA revolves around girly clothes adorned with frills and intricate designs that require significant drawing effort. The initial version lacks well-organized tags and is mainly based on illustration materials. To improve the model, including photos with mannequins and close-up images would be essential. Although I attempted to use LoraPlus, I couldn't fully leverage its potential.
While appreciating the imperfections, the model is reasonably complete for a first release.
---
### Training Parameters
Key Points
- Network Rank : 16
- Learning Rate : UNet 0.001 / Text Encoder 0.0001
- Scheduler : CosineAnnealingLR (T_max=860, eta_min=1e-7)
---
### Example Execution Command
---
Details
Files
Available On (5 platforms)
Same model published on other platforms. May have additional downloads or version variants.