Type | |
Stats | 687 |
Reviews | (81) |
Published | Jun 16, 2024 |
Base Model | |
Hash | AutoV2 DF3DCDB9F8 |
V3.0: Combination of style and prompt recognition upgrades. Images come out very clean with a very unique style. Jack of all trades type of checkpoint. This is a continuation of V2.0, Wild_Child is still it's own thing.
Wild_Child: This model can be "wild" with how it responds to some prompts. The style is very unique and looks completely new. I like this one for when I want a certain look I can't get with any other model. Mild lighting and shadows. This model is more for playing around with and being surprised by results, such as abstract works.
Lightning models best results settings:
Sampler: dpmpp_2m_sde_gpu
Scheduler: sgm_uniform
CFG: 1.0-1.5
Steps: 10
V.3 and Wildchild settings I use comfyUI :
Steps: I use 28
cfg: I use 3.5
dpmpp_3m_sde_gpu
sgm_uniform
Vae is baked in
For the lightning model: The lightning model has good results with a little different style, but the main point is for speed. This model uses the 8 step version of lighting.
Lightning 8 step version.
Configuration I use:
Steps: 8-10
CFG: 1-2, I like 1.5 best (1 is more natural and less bright and runs fastest)
Sampler: dpmpp_2m_sde_gpu
Scheduler: sgm_uniform
Don't use FreeU, some images look good with it, but it breaks prompting accuracy.