Artifida by Gourieff

Fast and beautiful LCM model

No LCM LoRA is required

No negative prompt is required

Configuration for best results:

Sampler: LCM

Steps: 9-13

CFG Scale: 1

WxH: 960×960

Clip Skip: 2 (if you need more realism)

Recipe:

1. [85%] p-AI-nter_v0.2* + [15%] protogen_v2.2

2. [25%] <1> + [75%] (mira-v1.1* [60%] + menheraV2Experimental [40%])

3. [50%] ([15%] <2> + [85%] mira-v3.0–4500steps*) + [50%] ([25%] <2> + [75%] mira-v3.0–5000steps*)

4. [60%] <3> + [40%] photon_v1

5. <4> <- LCM_LoRA_Weights_SD15:1.0 <- ip-adapter-faceid_sd15_lora:0.666

*”p-AI-nter_v0.2″(public model) and “mira”(private models) – trained by me