https://civitai.com/models/2270401?modelVersionId=2700412
--
distilled 版本:
CFG:1，4步。
CFG:1.5，5~8步。
distilled Version:
LoRA.CFG: 1 with 4 steps.
CFG: 1.5 with 5~8 steps.
--
Base 版本:
使用4步驟lora生成圖片的速度較快。
下載Z-Image-Fun-Lora-Distill-4-Steps-2602-ComfyUI lora。
CFG:1，4步。
CFG:1.5，5~8步。
將Z-Image-Fun-Lora-Distill-4-Steps-2602-ComfyUI lora的lora權重設定為1。
--
不使用4步驟lora時:
- Steps: 30～50
- cfg: 3～5
--
某些的Z-Image Turbo的lora可以使用。
由於Z-image Base對提示詞的反應較為靈敏，不能直接複製Z-Image Turbo的提示詞，需重新編寫提示詞。
Z-image Base生成的圖片越大張時，有可能出現一個人物有兩顆頭的問題，替換種子重新出圖即可解決問題。
--
Base Version:
Using a 4-step LoRA allows for faster image generation.Download the Z-Image-Fun-Lora-Distill-4-Steps-2602-ComfyUI LoRA.CFG: 1 with 4 steps.
CFG: 1.5 with 5~8 steps.
Set the LoRA weight of Z-Image-Fun-Lora-Distill-4-Steps-2602-ComfyUI to 1.
--
When not using the 4-step LoRa:
- Steps: 30～50
- cfg: 3～5
--
Some Z-Image Turbo LoRAs can be used.
Because Z-Image Base responds more sensitively to prompts, you cannot directly copy prompts from Z-Image Turbo and need to rewrite the prompts.
Larger images generated by Z-image Base may have the issue of a person having two heads. Replacing the seed image and regenerating the image will solve the problem.
我已將模型上傳至runninghub。
I have uploaded the model to runninghub.
PornMaster_z-image_base_V0.1_fp8:
https://www.runninghub.ai/model/public/2024107278651105282/?inviteCode=rh-v1304
PornMaster_z-image_base_V0.1_bf16:
https://www.runninghub.ai/model/public/2024107273051709442/?inviteCode=rh-v1304
--
不要問我如何安裝的問題與comfyui如何使用。
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.
Do not ask me questions about how to install it or how to use ComfyUI.
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.