🥠GhostBubbleMango V2 — Anima
Version 2 of GhostBubbleMango!
This version builds upon the original GhostBubbleMango merge with an updated model blend and an adjustment to the baked-in Turbo LoRA strength.
For V2, the baked-in Turbo LoRA strength has been reduced from 1.0 to 0.5, with the goal of providing more flexibility in prompt interpretation, detail, and overall image generation while retaining the benefits of Turbo.
This version combines GhostBubbleHybrid V3 and Pink Alchemy Anima, bringing together their respective styles into an updated GhostBubbleMango checkpoint.
settings:
CFG:1-3 Steps:12-20 Sampler: Euler A, er_sde
What's changed in V2?
Updated model merge.
Baked-in Turbo LoRA strength reduced from 1.0 to 0.5.
Experimental adjustment intended to improve prompt flexibility and reduce some of the restrictions associated with stronger Turbo influence.
Updated blend of character styles and rendering characteristics.
Source Models
Notes
This is an experimental update. Results may vary depending on prompt, sampler, steps, CFG, and LoRA combinations.
Thanks for testing GhostBubbleMango, and I hope you enjoy V2!
Description
🥠GhostBubbleMango V2 — Anima
Version 2 of GhostBubbleMango!
This version builds upon the original GhostBubbleMango merge with an updated model blend and an adjustment to the baked-in Turbo LoRA strength.
For V2, the baked-in Turbo LoRA strength has been reduced from 1.0 to 0.5, with the goal of providing more flexibility in prompt interpretation, detail, and overall image generation while retaining the benefits of Turbo.
This version combines GhostBubbleHybrid V3 and Pink Alchemy Anima, bringing together their respective styles into an updated GhostBubbleMango checkpoint.
What's changed in V2?
Updated model merge.
Baked-in Turbo LoRA strength reduced from 1.0 to 0.5.
Experimental adjustment intended to improve prompt flexibility and reduce some of the restrictions associated with stronger Turbo influence.
Updated blend of character styles and rendering characteristics.
Source Models
Notes
This is an experimental update. Results may vary depending on prompt, sampler, steps, CFG, and LoRA combinations.
Thanks for testing GhostBubbleMango, and I hope you enjoy V2!



















