[ Work in Progress ]
Updated to Source 2: Better image quality, revised tagging, character and location tags
The trigger words are: Source Engine, 3D,
Characters that are baked in:
Alyx is triggered by: AlyxV, Dark Skin, Jacket
Judith can be triggered by: JudithM, sweater, hair ornament
Female 01 can be triggered by: Female 01, hair bun
Female 02 can be triggered by: Female 02, ponytail
Combine are triggered with: Combine, Combine Mask, Combine uniform
Tags that assist with location:
indoors
red couch
rug
window
laboratory
facility
outdoors
gm_construct
blue sky
clouds
grass
building
scenery
fence
courtyard
concrete wall
If you're sometimes getting bigger heads, put this in negative:
source_anime
To get results akin to the example images I recommend using Latent Upscaling with nearest-exact at 1.50.
I plan on updating this frequently but I've never made LoRAs before and that costs buzz lol
Thanks for downloading, excited to see what y'all post!
Description
First ever LoRA trained on Civit, I absolutely plan to rework and perfect this. At this point im just checking settings within the model editor for further upgrades. This was trained on 50 Epochs, this is Epoch 37. Keeping it at 0.9 strength seemed to work for me. I do know that the generations get scuffed but using Latent Upscaling I get pretty ???? accurate pictures to the game.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.


