ponyv5_noobV065S_1_adamW-000013
Back

ponyv5_noobV065S_1_adamW-000013
10 0 2

2D

ponyv5_noobV065S_1_adamW-000013
ponyv5_noobV065S_1_adamW-000013

Intro:

A style LoCon trained on pony based model images collected from Civitai site with "most collections" and "most reactions".

This is a style LoCon trained on pony model images with the most likes and collections from Civitai.

This lora does not intend to simulate any specific artist style or technique. It MIGHT reflects community taste and the visual attractiveness of a picture to a certain extent. Styles may change subtly depending on different prompts.

This lora does not aim to replicate the style or techniques of any specific artist. It may reflect community aesthetics and the visual appeal of images to some extent. Subtle style changes may occur under different prompts.

Usage:

Versions before V2 do not have specific trigger words. Please use the quality tags provided with the corresponding model.

For V3 and later versions, the following tags were trained:

Versions before V2 do not have specific trigger words. Please use the quality tags provided with the corresponding model.

For V3 and later versions, the following tags were trained:

positive:

masterpiece, best quality, very aesthetic

negative:

worst quality, low quality, displeasing

You can edit the prompts based on this.

Data Generation:

v6:

Added over 500 new images, some of which are selected from Flux. I removed some older images that I deemed to be of lower quality.

The total number of images in data set now exceeds 3,000, with more than 20 concepts manually enhanced/edited across 6 versions of the dataset.

The model’s rank has been increased as well.

Added 500 new images, some of which were selected from images generated by Flux. Removed some older images deemed to be of lower quality.

Now the total number of images exceeds 3,000, with more than 20 concepts manually enhanced/edited across six versions of the dataset.

The model’s rank has been increased.

v5.9:

The model's performance is not as expected, but I believe the images in the training data set are just fine. I'm planning to adjust the tags manually and see how will the results change.

The model's performance did not meet expectations, but I believe the training dataset images are fine. Planning to manually adjust the tags to see if the results change.

2025/1/3 Update:

Manually updated some tags, but they seem unrelated to brightness and colors. Tentatively guessing it might be related to noise offset.

Manually updated some tags, but they seem unrelated to brightness and colors. Tentatively guessing it might be related to noise offset.

This model is sourced from an external transfer (transfer address: https://civitai.com/models/856285?modelVersionId=1137323 ）,if the original author has objections to this transfer, you can click，
Appeal
We will, within 24 hours, edit, delete, or transfer the model to the original author according to the original author's request

user_8tpxymbh

user_8tpxymbh

2D

Model Information

Active
Original author：
Dajiejiekong
Model Type：
LoRA
Basic Model：
Other
Resource Name：
models/loras/ponyv5_noobV065S_1_adamW-000013.safetensors
MD5：
2eba565765876f53d3086bd5a5eb13c5

Intro:

A style LoCon trained on pony based model images collected from Civitai site with "most collections" and "most reactions".

This is a style LoCon trained on pony model images with the most likes and collections from Civitai.

This lora does not intend to simulate any specific artist style or technique. It MIGHT reflects community taste and the visual attractiveness of a picture to a certain extent. Styles may change subtly depending on different prompts.

This lora does not aim to replicate the style or techniques of any specific artist. It may reflect community aesthetics and the visual appeal of images to some extent. Subtle style changes may occur under different prompts.

Usage:

Versions before V2 do not have specific trigger words. Please use the quality tags provided with the corresponding model.

For V3 and later versions, the following tags were trained:

Versions before V2 do not have specific trigger words. Please use the quality tags provided with the corresponding model.

For V3 and later versions, the following tags were trained:

positive:

masterpiece, best quality, very aesthetic

negative:

worst quality, low quality, displeasing

You can edit the prompts based on this.

Data Generation:

v6:

Added over 500 new images, some of which are selected from Flux. I removed some older images that I deemed to be of lower quality.

The total number of images in data set now exceeds 3,000, with more than 20 concepts manually enhanced/edited across 6 versions of the dataset.

The model’s rank has been increased as well.

Added 500 new images, some of which were selected from images generated by Flux. Removed some older images deemed to be of lower quality.

Now the total number of images exceeds 3,000, with more than 20 concepts manually enhanced/edited across six versions of the dataset.

The model’s rank has been increased.

v5.9:

The model's performance is not as expected, but I believe the images in the training data set are just fine. I'm planning to adjust the tags manually and see how will the results change.

The model's performance did not meet expectations, but I believe the training dataset images are fine. Planning to manually adjust the tags to see if the results change.

2025/1/3 Update:

Manually updated some tags, but they seem unrelated to brightness and colors. Tentatively guessing it might be related to noise offset.

Manually updated some tags, but they seem unrelated to brightness and colors. Tentatively guessing it might be related to noise offset.

This model is sourced from an external transfer (transfer address: https://civitai.com/models/856285?modelVersionId=1137323 ）,if the original author has objections to this transfer, you can click，
Appeal
We will, within 24 hours, edit, delete, or transfer the model to the original author according to the original author's request