CyberHarem/venti_genshin

LoRA model of venti/ウェンティ/温迪 (Genshin Impact)

What Is This?

This is the LoRA model of waifu venti/ウェンティ/温迪 (Genshin Impact).

How Is It Trained?

• This model is trained with kohya-ss/sd-scripts, and the test images are generated with a1111's webui and API sdk.
• The auto-training framework is maintained by DeepGHS Team. The architecture of base model is is SD1.5.
• Dataset used for training is the stage3-p480-1200 in CyberHarem/venti_genshin, which contains 1292 images.
• Trigger word is venti_genshin.
• Pruned core tags for this waifu are multicolored hair, black hair, braid, twin braids, blue hair, gradient hair, green eyes, hat, beret, green headwear, bow, hair ornament, hair flower. You can add them to the prompt when some features of waifu (e.g. hair color) are not stable.
• For more details in training, you can take a look at training configuration file.
• For more details in LoRA, you can download it, and read the metadata with a1111's webui.

How to Use It?

After downloading the safetensors files for the specified step, you need to use them like common LoRA.

• Recommended LoRA weight is 0.5-0.85.
• Recommended trigger word weight is 0.7-1.1.

For example, if you want to use the model from step 680, you need to download 680/venti_genshin.safetensors as LoRA. By using this model, you can generate images for the desired characters.

Which Step Should I Use?

We selected 5 good steps for you to choose. The best one is step 680.

980 images (1009.81 MiB) were generated for auto-testing.

Here are the preview of the recommended steps:

Step	Epoch	CCIP	AI Corrupt	Bikini Plus	Score	Download	pattern_0	pattern_1	pattern_2	pattern_3	pattern_4	pattern_5	pattern_6_0	pattern_6_1	pattern_7_0	pattern_7_1	pattern_8_0	pattern_8_1	pattern_8_2	pattern_9	pattern_10	portrait_0	portrait_1	portrait_2	full_body_0	full_body_1	profile_0	profile_1	free_0	free_1	short	shirt_0	shirt_1	uniform_0	uniform_1	uniform_2	suit_0	suit_1	jacket_0	jacket_1	swim_0	swim_1	swim_2	sit	squat	kneel	jump	crossed_arms	angry	smile	cry	grin	n_stand_0	n_stand_1	n_stand_2
680	4	0.981	0.981	0.816	0.827	Download
2890	17	0.982	0.975	0.811	0.826	Download
2720	16	0.980	0.979	0.810	0.794	Download
3230	19	0.979	0.963	0.817	0.776	Download
3060	18	0.978	0.984	0.820	0.773	Download

Anything Else?

Because the automation of LoRA training always annoys some people. So for the following groups, it is not recommended to use this model and we express regret:

1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.

All Steps

We uploaded the files in all steps. you can check the images, metrics and download them in the following links:

• Steps From 1870 to 3400
• Steps From 170 to 1700