File size: 1,607 Bytes
54ad98d |
1 2 3 4 5 6 7 8 |
{
"sha256": "843E039A5C34B541D4A3997CE5B50EC1FA72C6E3A28A1C2307E3C7E978532BCD",
"modelId": 1070616,
"modelVersionId": 1395454,
"activation text": "",
"description": "-------------\ud835\udd39\ud835\udd56\ud835\udd6a\ud835\udd60\ud835\udd5f\ud835\udd55 \ud835\udd46\ud835\udd57 \ud835\udd50\ud835\udd60\ud835\udd66\ud835\udd63 \ud835\udd40\ud835\udd5e\ud835\udd52\ud835\udd58\ud835\udd5a\ud835\udd5f\ud835\udd52\ud835\udd65\ud835\udd5a\ud835\udd60\ud835\udd5f----------NOTE: ryosios text encoder (NoobAI fault, not my lora) is too heavy, try to lower down weight2/6/2025: Looks like big lora size is not a great idea. Loss value is useless..?2/7/2025: Loss value is useful... TIA is very close to higher level AND smaller lora file size\ud83e\udd73\ud83e\udd73\ud83e\udd732/8/2025: paper thingy2/10/2025: CLIP Improvement (Cancelled, Fail)2/11/2025: Due to CLIP Limitations, ThisIsntAI cannot go further.This is where my broken lora or the good ones are posted here.This is settings for Euler Fan.:Euler A\nAlign Your Steps GITS or Align Your Steps\nSampling steps: more than 20\nMahiro CFG for reForge or comfyui Enabled \nCFG Scale: 4-5\nNo NegativeThis is settings Another:Restart \nAlign Your Steps GITS\nSampling steps: 10-20\nMahiro CFG for reForge or comfyui Enabled \nCFG Scale: 4\nNo NegativeThis is settings Best:https://github.com/pamparamm/sd-perturbed-attention https://github.com/pamparamm/sd-perturbed-attentionRestart \nAlign Your Steps GITS\nSampling steps: 10 or 20\nMahiro CFG for reForge or comfyui Enabled \nCFG Scale: 1-2\nNo Negative",
"sd version": "SDXL"
} |