A lora for the character Mina Ha from the game Deadlock.

V1.1 should work almost identically to v1.0, only you can use mina deadlock in place of mina_deadlock and you can use mina_umbrella for better prompting for her umbrella.

Main Trigger Words

• mina_deadlock - prompts for the character Mina Ha,

• mina_outfit - prompts for mina's outfit

Prompt as mina_deadlock wearing her mina_outfit for best effect.
You can also describe other characters wearing mina_outfit or mina_deadlock wearing other outfits.

WARNING: I've noticed that the results from my own renders through ComfyUI are vastly different from my results using CIVITAI. I don't know how exactly they run Anima models so use at your own risk. You can download my images for the ComfyUI setup, or make sure to use these models:
unet: anima-base-1.0
clip: qwen_3_0.6b_base
vae: qwen_image_vae

Additional Trigger Words

• umbrella - Has her holding her umbrella. often appears just by prompting mina_outfit

• skirt - sometimes her skirt morphs into shorts if you don't say skirt in the prompt,

• handbag - She has a red handbag that is a part of her official outfit, but is almost always omitted in people's illustrations, so it has to be prompted for 😅

• sash - Her official outfit wears a sash, not a belt! prompt sash to ensure that happens.

Misc Considerations

I made this lora as a test for how small and effective anima loras could get. I made 2 versions of this lora, one with twice the size (Network Dim 16) but didn't notice any significant difference in concepts, so decided to just release this smaller model.

There is still a bit of concept bleed with mina_outfit with the outfit being not completely associated with the token. I'll blame that on the dataset being mostly Mina in her default outfit. Probably could be fixed in the future if I balance the dataset better or get more examples...