下載前請仔細閱讀使用說明，否則將無法正確生成圖片。
Please read the instructions carefully before downloading, otherwise the image will not be generated correctly.
--
Pornmaster Z Image Turbo Workflow
Pornmaster Z Image Base t2i Workflow
--
2026/01/30: V3
V3版本基於Z Image Base訓練，可在Z Image Base和Z Image Turbo上使用。
在Z Image Base上使用時建議下載Z-Image-Fun-Lora-Distill-4-Steps-2602-ComfyUI lora，4步即可生成圖片。
解析度為1280p，使用H200 SXM訓練。
V3版本沒有訓練人臉，不會影響Z Image中的內建人物，並且對於Z Image的原始風格影響較小。
建議將A和B版本都下載來使用，這樣組合起來會更靈活。
V3分為A和B版本，A版本訓練步驟較低，B版本訓練步驟較高。
在Z Image Turbo上使用時:
當A和B一起使用時權重都設定為”1.25~1.75”，當A或B單獨使用時，權重設定為”2~3”。
V3版本lora在原版的Z Image Turbo上使用時，可與人物lora一起使用。
(注意:我只測試我自己練的人物lora.)
在Z Image base上使用時:
當A和B一起使用時權重都設定為”0.6”，當A或B單獨使用時，權重設定為”0.8~1”。
The V3 version is trained based on Z Image Base and can be used with both Z Image Base and Z Image Turbo.
When using it with Z Image Base, it is recommended to download the Z-Image-Fun-Lora-Distill-4-Steps-2602-ComfyUI LoRA, which can generate images in just 4 steps.
The resolution is 1280p, trained using H200 SXM.
The V3 version does not include face training, so it will not affect the built-in characters in Z Image and has minimal impact on Z Image’s original style.
It is recommended to download and use both the A and B versions for more flexible combinations.
V3 is divided into A and B versions: the A version is trained with fewer steps, while the B version is trained with more steps.
When using with Z Image Turbo:
· If using A and B together, set both weights to “1.25–1.75”.
· If using A or B individually, set the weight to “2–3”.
· When the V3 LoRA is used with the original Z Image Turbo, it can be combined with character LoRAs.
(Note: I have only tested this with my own trained character LoRAs.)
When using with Z Image Base:
· If using A and B together, set both weights to “0.6”.
· If using A or B individually, set the weight to “0.8–1”.
--
2025/12/05: V2
A lora或B lora可單獨使用，A訓練步驟較低，B訓練步驟較高，當A和B一起使用時只需LORA權重0.4就可生效。
但是要組合和其它LORA時，則必須A或B單獨使用。
此LORA會影響人臉，如果要還原內建人物的臉則必須進行面部修復。
或是使用A和B一起使用並且權重0.4即可降低對內建人物臉部的影響。
使用H200 SXM訓練。
--
Lora A or Lora B can be used individually. Lora A has a lower training step count, while Lora B has a higher training step count. When A and B are used together, a Lora weight of 0.4 is sufficient for effectiveness.
However, to combine them with other Lora types, either A or B must be used individually.
This Lora type affects the face; facial retouching is necessary to recreate the built-in character's face.
Alternatively, using A and B together with a weight of 0.4 can reduce the impact on the built-in character's face.
Training is performed using H200 SXM.
--
觸發詞(Trigger words):
pornmaster flat breasts, a woman with flat chest,
--
我的其他檢查站和Lora。
My other checkpoints and Lora.
--
客製化lora:我的Telegram ID:@iamddtla0620
我的微信ID:iamddtla
我的line ID:iamddtla
時間寶貴，請直接說明來意，例如:訂製lora.
Customized lora: My Telegram ID: @iamddtla0620
My WeChat ID: iamddtla
My Line ID: iamddtla
Time is precious, please state your intention directly, for example: customized LORA.