Downloads · 30 days
0
CyberHarem/rumi_bluearchive
rumi_bluearchive is a text-to-image model from CyberHarem. Use it when you need an image from a text prompt. The card lists the license as mit.
This is the LoRA model of waifu rumi/朱城ルミ/瑠美 (Blue Archive).
Downloads · 30 days
0
Access
Public
Updated Mar 25, 2024
Repo size
14.7 GB
Likes
0
Public
Click a slice to open those files.
.zip735 MB · 50%
From the Hugging Face model README
This is the LoRA model of waifu rumi/朱城ルミ/瑠美 (Blue Archive).
SD1.5.stage3-p480-1200 in CyberHarem/rumi_bluearchive, which contains 520 images.rumi_bluearchive.brown hair, animal ears, long hair, breasts, fox ears, halo, hair between eyes, large breasts, purple eyes, crossed bangs, red halo, very long hair. You can add them to the prompt when some features of waifu (e.g. hair color) are not stable.After downloading the safetensors files for the specified step, you need to use them like common LoRA.
For example, if you want to use the model from step 2960, you need to download 2960/rumi_bluearchive.safetensors as LoRA. By using this model, you can generate images for the desired characters.
We selected 5 good steps for you to choose. The best one is step 2960.
630 images (648.16 MiB) were generated for auto-testing.

The base model used for generating preview images is meinamix_v11.
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_0 | pattern_5_1 | portrait_0 | portrait_1 | portrait_2 | full_body_0 | full_body_1 | profile_0 | profile_1 | free_0 | free_1 | shorts | maid_0 | maid_1 | miko | yukata | suit | china | bikini_0 | bikini_1 | bikini_2 | sit | squat | kneel | jump | crossed_arms | angry | smile | cry | grin | n_lie_0 | n_lie_1 | n_stand_0 | n_stand_1 | n_stand_2 | n_sex_0 | n_sex_1 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2960 | 20 | 0.973 | 0.993 | 0.843 | 0.881 | Download | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() |
| 2664 | 18 | 0.968 | 0.987 | 0.844 | 0.848 | Download | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() |
| 2368 | 16 | 0.961 | 0.992 | 0.847 | 0.806 | Download | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() |
| 4144 | 28 | 0.953 | 0.973 | 0.846 | 0.749 | Download | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() |
| 1184 | 8 | 0.953 | 0.995 | 0.842 | 0.743 | Download | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() |
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:
We uploaded the files in all steps. you can check the images, metrics and download them in the following links: