Glow n Flow (P4A)

trained with kohya_ss (edg settings)

dana_ulama dataset deviantart.com/dana-ulama/gallery

kelvinsf dataset deviantart.com/kelvinsf/gallery/86790128/fluid-sculpture

trigger "p4a psychedelic" + EasyNegative

huggingface.co/LibreSD/Various/resolve/main/EasyNegative.safetensors

huggingface.co/LibreSD/Various/resolve/main/EasyNegativeV2.safetensors

samples civitai.com/models/154028/glow-n-flow-p4a

Merge Info

GnF64

• step1 = dana_ulama 0.6 + kelvinsf 0.4
• step2_a = step1-camelliamix_v3 0.6 + step1-greymix_v2 0.4
• step2_b = step1-counterfeit_v3 0.6 + step1-nabimix_v2 0.4
• gnf64_v1_a = step2_a 0.6 + step2_b 0.4
• gnf64_v1_b = step2_b 0.6 + step2_a 0.4

GnF82

• step1 = dana_ulama 0.8 + kelvinsf 0.2
• step2_a = step1-camelliamix_v3 0.6 + step1-greymix_v2 0.4
• step2_b = step1-counterfeit_v3 0.6 + step1-nabimix_v2 0.4
• gnf82_v1_a = step2_a 0.6 + step2_b 0.4
• gnf82_v1_b = step2_b 0.6 + step2_a 0.4

P4A Glow

• step1 = p4a-step2 0.6 + dana_ulama 0.4
• step2_a = step1-camelliamix_v3 0.6 + step1-greymix_v2 0.4
• step2_b = step1-counterfeit_v3 0.6 + step1-nabimix_v2 0.4
• p4a_glow_v1_a = step2_a 0.6 + step2_b 0.4
• p4a_glow_v1_b = step2_b 0.6 + step2_a 0.4

P4A Flow

• step1 = p4a-step2 0.6 + kelvinsf 0.4
• step2_a = step1-camelliamix_v3 0.6 + step1-greymix_v2 0.4
• step2_b = step1-counterfeit_v3 0.6 + step1-nabimix_v2 0.4
• p4a_flow_v1_a = step2_a 0.6 + step2_b 0.4
• p4a_flow_v1_b = step2_b 0.6 + step2_a 0.4

base models and other essentials huggingface.co/LibreSD