Objective
Testing the "Emotion Sliders" lora
Environment
For this test I will use:
Stable Diffusion with Automatic1111 (https://github.com/AUTOMATIC1111/stable-diffusion-webui)
Checkpoint
The Truality Engine (https://civitai.com/models/158621/the-truality-engine)
Models
Brooke (https://civitai.com/models/277465?modelVersionId=312627)
Maria Vicious (https://civitai.com/models/186924/maria-vicious)
Manuela Vicious (https://civitai.com/models/234362?modelVersionId=264258)
Prompt
Positive Prompt
(Shot on Aaton LTR 54) DV_Smorrebrod_Vicious (CYAN BIKINI:1.4)(blonde hair:1.5) insanely detailed and intricate, character, hypermaximalist, beautiful, exotic, revealing, appealing, attractive, amative, hyper realistic, (super detailed:1.3), (Palms, Beach, Sunshine:1.4)(skinny, slim:1.4) ) (abs:0)
Negative Prompt:
Watermark, text, (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs,nipples,
Other
Steps: 36
Sampler: DPM++ 2M SDE Karras
CFG scale: 3.5
Seed: 2317953536
Size: 512x768
Model: theTrualityEngine_trualityENGINEPRO
Set the Script X/Y/Z
On the script we need to set :
Prompt S/R with the different values of the Lora
(abs:0), (abs:0.6),(abs:1),(abs:1.5),(abs:1.8),(abs:2),(abs:2.2)
and the names of the girls:
DV_Smorrebrod_Vicious ,DV_Maria_Vicious ,DV_Manuela_Vicious
Generate the Images
The "abs" prompt start to works well after (abs:1) , before I don't see any visible effect.
(Abs:2.2) it is too much.
Smorrebrod Vicious
Maria Vicious
Manuela Vicious
I have also generated some video with animateDiff with the same prompt.
The Abs result works well also on videos.
If you have any question write a comment.