This is a collection containing multiple variants for a Character LoRA. See Description for more information. This version was previously called SangoV2.5. If you like my work and would like to leave a review, I mean.. feel free to. I do this for purely for fun - nothing else.<hr />Trained on <a target="_blank" rel="ugc" href="https://civarchive.com/models/221751?modelVersionId=469243">The Deep Dark v6.0</a> Dataset is from Inuyasha: The Final Act. Tagged backgrounds. Dataset consists of 188 images. Trained on site, used 25 epochs, 7 repeats, 4 batch size or 8225 steps. It is overtrained. As a result of overtraining, bath scenes are dark. Weight/Setting Suggestions (Estimate)<ul><li>Lora Weight: 0.5 ~ 0.8</li><li>CFG Scale: 5 ~ 10</li><li>Sampler: Euler A, DPM++ series (unsure)</li><li>Steps: 20 ~ 40</li><li>Denoise: 0.5 ~ 0.75</li><li>Resolution: 512x512 (use upscaler/hires)</li></ul> See the gallery for prompt guidance. I have provided some x/y/z plots in the gallery, should give you an idea.<hr /><h3 id="prompt-usage-0jik04z7m">Prompt Usage</h3>The trigger word is Sango. I didn't use unique tags for clothing. Here are two prompt examples. Hair color, breast size, eye color, hair style can be modified. Hiraikotsu wasn't tagged. Kimono Outfit<pre><code>Sango, 1girl, solo, brown eyes, brown hair, black hair, long hair, low-tied long hair, makeup, bangs, kimono, skirt, green skirt, anime coloring, retro artstyle</code></pre>Armor Outfit<pre><code>Sango, 1girl, solo, brown eyes, brown hair, black hair, ponytail, makeup, bangs, armor, shoulder pads, anime coloring, retro artstyle</code></pre>Be sure to make use of quality tags, body tags, expressions. Have some decent negatives. You can reference my gallery for examples. Anything else I didn't mention is probably not worth mentioning.

Sango (Inuyasha: The Final Act) | SDXL 1.0 | The Deep Dark v6.0 | SangoV1

This is V3, but with a different trained model (Prefect Pony XL 4.0). Nozzle was turned to the right (more steps, overtrained). Trigger Words are basic examples. You will need to make use of body angles, backgrounds and more to make them look better.See Description for more information.

SangoV5.safetensors

SangoV4.safetensors

SangoV4

SangoV1

SangoV2

This is a collection containing multiple variants for a Character LoRA. See Description for more information. This version was previously called SangoV5. If you like my work and would like to leave a review, I mean.. feel free to. I do this for purely for fun - nothing else.<hr />Trained on <a target="_blank" rel="ugc" href="https://civarchive.com/models/439889?modelVersionId=1047139">Prefect Pony XL v4.0</a> Dataset is from Inuyasha: The Final Act. Backgrounds removed. Trained on site. 7550 steps (151 images @ 20 epochs, 10 repeats, 4 batch size). Overtrained. Start at lower weights and make your way up. By this I mean a lora weight of 0.5, cfg scale of 5. See trained model page and gallery for others generally.<hr /><h3 id="prompt-usage-k9ue4qb4s">Prompt Usage</h3>The trigger word is Sango. I didn't use unique tags for clothing. Here are two prompt examples. Hair color, breast size, eye color, hair style can be modified. Try 'giant boomerang' for Hiraikotsu. Untested. Kimono Outfit<pre><code>Sango, 1girl, solo, brown eyes, brown hair, black hair, long hair, low-tied long hair, makeup, bangs, kimono, pink kimono, skirt, green skirt, anime coloring, retro artstyle</code></pre>Armor Outfit<pre><code>Sango, 1girl, solo, brown eyes, brown hair, black hair, ponytail, makeup, bangs, black bodysuit, shoulder pads, anime coloring, retro artstyle</code></pre>Be sure to make use of quality tags, body tags, expressions. Have some decent negatives. You can reference my gallery for examples. Anything else I didn't mention is probably not worth mentioning

Files with SHA256: 234502a1860eb6de65dd0184d4a5fbe8522540029ce35882ea033b66fa4dc9e0