This version is not very user-friendly at the moment.
There are also many instances where the caption is not very accurate, making it difficult to achieve the desired effects.
The training of this model and the images it generates are solely for learning purposes.
I did nothing, I'm just a porter.
You could find the example prompts from the images above.
Recommended weight: 1~0.6, adjust as needed until the character's appearance meets your requirements.
Upscale value recommendation is around 1.5, denoising strength is 0.2
Due to the poor quality of the images collected, this model is prone to issues such as blurriness, fragmentation, and tearing, which can be alleviated by adjusting the model's weights.
I think better image datasets are needed to improve the model's performance.
Collected 22 images, but in reality, they were obtained by splitting a few images into full body, cowboy shot, upper body, portrait, and close-up. There is overfitting, and the portrayal of hands is not very good.
Continuous adjustment of the prompt words is needed to achieve a good representation.