NOTE : Base model : Z Image Turbo & Flux1
Showcase images were created with ComfyUI and are in PNG, include metadata & workflow.
VERY IMPORTANT NOTE :Do not like my models, do not give me buzz, do not follow me, otherwise you will be reported to Civitai for attempted corruption
Description
Model trained on civitai with 46 images
Recommended resources : Fluxmania V
Recommended settings : dpmpp_2m or heunpp2 / sgm_uniform / 25 steps / guidance : 2.5 to 4.0
Weighting When used alone: around 0.5
If combined with other LoRAs, the weight must be significantly reduced.
FAQ
Comments (3)
Can you tell us the characteristics of each version? There are some parts that are hard to know
The "Rembrandt Lighting" model was trained on portraits with this particular lighting style. So, it's portrait-oriented chiaroscuro.
Synesthesia is similar to chiaroscuro but more general, with the effect of intensifying existing lighting (without creating new lighting).
DSL One is also chiaroscuro-based, with shadow intensification, halftone, and hazy atmospheres.
Black Illusion brings out uniformly dark lighting.
To be honest, I never have time to test in depth, so have your own approach to these models.
Thank you for the details :)@Adel_AI
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.