**************** About Version & Training Set ****************
This is a Lora for adjusting strokes. It has a greater impact on the background/environment. The higher the weight, the less detail the environment has. It can be used to draw portraits, landscapes, objects, etc., and can be used to adjust oil painting styles or ink painting styles. The training set uses only pure stroke textures. When paired with checkpoints, objects can be shaped from these abstract strokes.
Use brush strokes to outline the background and large blocks of color while highlighting the main details of the painting. The contrast between the expressive power of wild brushstrokes and the depicted subject makes the picture more tense, and also makes the original painting more tense. The picture is more about the relationship between virtuality and reality, losing some details and gaining a more "ethereal" artistic conception.
There are currently two versions:
----> V1.0 More rough and straight strokes, with a small adjustable range of thickness. Due to the impact on the background, generating images dominated by objects/portraits has a higher weight than scenes.
----> V2.0 This version has a new training set, more strokes, slightly smaller strokes, and a larger adjustable range, but still has more background/environment impact, and the fit weights have changed from the first version.
----> Training model: helloyoung25d_V15j
----> Trigger word: None
----> Training set V1.0: 70 images | Number of steps: 6300
----> Training set V2.0: 171 images | Number of steps: 7695
【Disclaimer】
1. In principle, this model is only used for communication and learning, and the model and generated diagrams are not allowed to be used for commercial purposes.
2. Users shall use it under the conditions of complying with the laws and regulations of their country and these terms of service. Any intellectual property disputes arising from the content generated based on this model shall be handled by the user themselves.
3. This model may not be integrated into any third-party software or service without the authorization and consent of the author.
4. When generating images and publishing them on social media, the citation model and author must be noted.
********************** Recommendations **********************
----> Suggestions for using the checkpoint
More suitable for 25D/oil painting and some illustration models:
---->Lora weight suggestion
V1.0
Portrait/objects: 0.2<= Weight <=0.6
sence: 0.1<= weight <=0.3
* The weights used with different basic models will be slightly different, you can try from 0.3;
V2.0
Portrait/objects: 0.3<= Weight <=1
sence: 0.2<= weight <=0.5
* The weights used with different basic models will be slightly different, you can try from 0.4;
************************ XYZ Test Chart ************************
V1.0
V2.0
