Updated: Jul 19, 2024
style
爱门永存！今天的崩坏3是无敌的！
The base model used for training is Kohaku-XL Epsilon - rev2 , and it is recommended to use the prompt format suggested by KohakuXL. In addition to the basic effects, reasonable use can produce other styles and a series of additional effects. Please try it on your own. [All parameters of this model are configured and uploaded automatically]
How This Model Is Trained
This model is trained with kohya-ss/sd-scripts, the images are generated with a1111's webui
The auto-training framework is maintained by DeepGHS Team.
The step we auto-selected is 18 ep to balance the fidelity and controllability of the model.
Why Not Just Using The Better-Selected Images
Our model's entire process, from data crawling, training, to generating preview images and publishing, is 100% automated without any human intervention. It's an interesting experiment conducted by our team, and for this purpose, we have developed a complete set of software infrastructure, including data filtering, automatic training, and automated publishing. Therefore, if possible, we would appreciate more feedback or suggestions as they are highly valuable to us.
Why We Can't Accurately Generate the Desired Art Style
Our current training data is sourced from a variety of image websites. Predicting the specific art styles present in official images within a fully automated pipeline presents a significant challenge. As a result, the generation of art styles relies on clustering based on labels from the training dataset, striving for the best possible reproduction. We will continue to tackle this issue and seek optimization, but it remains a challenge that cannot be entirely resolved. The accuracy of art style reproduction is also unlikely to match the level achieved by manually trained models.
For the following groups, it is not recommended to use this model and we express regret:
Individuals who cannot tolerate any deviations from the original art style, even in the slightest detail.
Individuals who are facing application scenarios with high demands for accuracy in art style reproduction.
Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
Individuals who are not comfortable with the fully automated process of training art style models using LoRA, or those who believe that art style training must be done purely through manual operations to maintain the integrity of the original artistic vision.
Individuals who finds the generated image content offensive to their values.