Alexstrasza - The Life Binder (World of Warcraft Character LoRA)

“Do you think I have big mom energy?” - Alexstrasza in Dragonflight

This LoRA is designed to only work with Automatic1111 and its derivatives (Forge, ReForge, etc.). Results will be relatively horrible in ComfyUI and on CivitAI's image generation service. Therefore, I offer support for neither of them.

Click "Show More" to obtain the best results. Do not complain about horrible results if you are unwilling to take the time to read this through!

This is my first foray into character LoRAs. It was surprisingly simple compared to the photoreal models I typically train. My training method was simple. I extracted Alexstrasza's character model from the game, rendered it in 3D, and exported 814 images using various poses, angles, lighting, etc. I then grabbed 20 2D & 3D images from across the web, cleaned them up in Photoshop, and...viola! This came out much better than I expected considering that no cosplay or other photos were used in the character training data.

For those with Alexstrasza mommy issues (yeah, apparently that's a thing), this LoRA was not designed to produce grotesque, bloated, overweight renderings of her. You will either have to look elsewhere for that, or seriously up your prompting game. Asides for the NSFW support, I tried to keep this model as canon as possible.

Checkpoint Note:

While this LoRA was trained on the base SD1.5 checkpoint, it works incredibly well with the WaffleMix_v7 checkpoint. However, I just found that the creator removed it from CivitAI and moved it to Tensor.art. One may download it from there, or use an alternate model.

epiCPhotoGasm version X works well for photoreal, realistic, & 3D, while AniMerge v2.4 works well for 2D and some 3D.

MANDATORY Triggers

Alexstrasza, red hair, golden eyes, horns, long eyebrows, headdress, slim body

OPTIONAL Triggers

upper body, purple jewel, cleavage, fantasy armor, tabard skirt, pauldrons, gauntlets, glowing eyes

Prompt Format

Keep prompts and negatives as short and simple as possible. The format should look like:

a photo of ##Mandatory Triggers##, ##Optional Triggers##, ##the rest of your prompt##

NOTE #1: Disable face restoration if you wish to prompt "glowing eyes". It will negate the prompt.
NOTE #2: The following prompts are unreliable and may be fixed in a v2: gauntlets (sometimes show fingers), pauldrons (don't always get rendered). The following prompts are unreliable but are still required triggers: long eyebrows (often brown instead of red, sometimes way too short for canon), headdress (only partially renders sometimes)

Recommended Settings

Checkpoints: WaffleMix v7, epiCPhotoGasm version X, AniMerge v24. Other photoreal, realistic, & 2D models may work
Clip Skip: 1 (realism) or 2 (flexibility)
CFG: 3-8 (lower=realistic but less prompt accurate, higher=less realistic but more flexible)
Steps: 30-80 (less than 30 isn't recommended, except for 2D)
Sampler & Scheduler: DPM++ SDE Karras
Hires Fix scale: 2-4x
Hires Fix Steps: 12-20
Denoising Strength: 0.15-0.30
Upscaler: 4x_foolhardy_remacri

NSFW Support

I trained NSFW body parts seperately using real photos to increase detail and realism. These can be prompted but work much better when used in aDetailer.

aDetailer Female Breasts model v4.7 - Denoise Strength: 0.25-0.30

best quality, <lora:Alexstrasza_v1:1>breasts, ???????, 8K, high quality photography, Canon EOS R3

aDetailer ?????? / ????? Model v4.1 - Denoise Strength: 0.40-0.55

best quality, <lora:Alexstrasza_v1:1>pussy, high quality photography, Canon EOS R3