模型介紹為中英雙語,中文使用者可以關閉翻譯。
Trubo:
Pornmaster Z Image Turbo Workflow
Pornmaster Z Image Turbo Controlnet Workflow
PornMaster Z-image-turbo Controlnet: Cosplay - Anime to Realistic Style
PornMaster Z-image Increase realism & detail & sharpness
Pornmaster Z-Image Turbo i2i Workflow
PornMaster Simple 4X Magnification Workflow
Pornmaster Z-Image Turbo T2I Workflow-Double checkpoints & realism enhancer
--
Base:
Pornmaster Z Image Base t2i Workflow
--
Stable Diffusion WebUI Forge - Neo
--
如果使用nsfw的lora時,lora權重從0.1開始,然後逐漸增加調整權重。
(可以使用"Z-Image base"的lora,但是需要較高的權重。)
提高照片的解析度可以增加生成良好陰莖和陰部的成功率。
注意:有些人訓練的角色lora可以使用,有些人訓練的則無法使用,我並不知道原因。
如果對生成的性器官不滿意請使用PornMaster SDXL 或PornMaster flux2 klein 9b base 的Inpainting 檢查站來修復性器官。
--
When using nsfw's LoRa, start the LoRa weights from 0.1 and gradually increase them.
(You can use LoRa with a "Z-Image base", but it requires higher weights.)
Increasing the image resolution increases the success rate of generating good-looking penises and genitals.
Note: Some people's character lora training works, while others' does not; I don't know why.
If you are not satisfied with the generated sex organs, please use the Inpainting checkpoint of PornMaster SDXL or PornMaster flux2 klein 9b base to repair the sex organs.
--
Clip: qwen_3_4b.safetensors
Vae: ae.safetensors
--
我已將模型上傳至runninghub。
I have uploaded the model to runninghub.
PornMaster z-image Turbo V0.1_fp8:
https://www.runninghub.ai/model/public/2012876652145020930/?inviteCode=rh-v1304
PornMaster z-image Turbo V0.1_bf16:
https://www.runninghub.ai/model/public/2012891520348725249/?inviteCode=rh-v1304
PornMaster z-image Turbo V0.2_fp8:
https://www.runninghub.ai/model/public/2012870272323424257/?inviteCode=rh-v1304
PornMaster z-image Turbo V0.2_bf16:
https://www.runninghub.ai/model/public/2012858316384374786/?inviteCode=rh-v1304
PornMaster z-image Turbo V1_fp8:
https://www.runninghub.ai/model/public/2015385918403780610/?inviteCode=rh-v1304
PornMaster z-image Turbo V1_bf16:
https://www.runninghub.ai/model/public/2015380234719207425/?inviteCode=rh-v1304
PornMaster z-image Turbo V2_fp8:
https://www.runninghub.ai/model/public/2023636060722434049/?inviteCode=rh-v1304
PornMaster z-image Turbo V2_bf16
https://www.runninghub.ai/model/public/2023630811089604610/?inviteCode=rh-v1304
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
PornMaster_z-image_base_V0.1_distilled_fp8
https://www.runninghub.ai/model/public/2025833520878325762/?inviteCode=rh-v1304
PornMaster_z-image_base_V0.1_distilled_bf16
https://www.runninghub.ai/model/public/2025836003751108609/?inviteCode=rh-v1304
PornMaster z-image Turbo_5steps_V1_fp8
https://www.runninghub.ai/model/public/2026332244041801729/?inviteCode=rh-v1304
PornMaster z-image Turbo_5steps_V1_bf16
https://www.runninghub.ai/model/public/2026340550038786050/?inviteCode=rh-v1304
PornMaster z-image Turbo V3_fp8
https://www.runninghub.ai/model/public/2040397408881876993/?inviteCode=rh-v1304
PornMaster z-image Turbo V3.5_fp8
https://www.runninghub.ai/model/public/2041355991928807426/?inviteCode=rh-v1304
PornMaster z-image Turbo V3.5_fp16
https://www.runninghub.ai/model/public/2049373402028318721/?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.
Description
V3.5與V3版本相比:
主要是減少對角色LORA影響。
Compared with version V3, V3.5 mainly reduces the influence on character LoRA.
FAQ
Comments (54)
I'm not sure if you understood correctly... is version 3.5 better for using character LoRAs?
yes,Version 3 will still slightly affect the character Lora's face.
師兄,我真的很喜歡 3.0 版本。3.5 有哪些不同呢?我打算很快試試看。
I tested the character Lora. Version 3 affected the character's face, while version 3.5 had a smaller impact.
can we have bf16 version in future?🥺🥺
I'm using a new method to create the model, but the method I'm using currently can't create the BF16 version; the BF16 version will malfunction.
I consider this model from the author to be one of the best in terms of future prospects. As a basis for creating realistic deepfakes, it's simply top-notch. It's still lacking stability in complex poses, but if the author keeps up the good work, there's every chance this model will outshine any SDXL in terms of versatility, and even FLUX in terms of realism. Although this model already surpasses FLUX in a number of ways.
I agree the model is insane and allows for crazy fast prototyping.
I'm also using it in a workflow with flux-2-kv for the first step to increase variety and then let this model do the rest of the work. Works pretty well if the poses are not to complex
@wwall Increasing shift fixes complex poses for me though at the cost of some detail. for diversity if you use comfyui i use this node https://github.com/facok/ComfyUI-DiversityBoost
Talking about deepfakes is a good way to get a model pulled just fyi
您好,Turbo V3模型无法下载!点击下载后一直刷新页面,无法跳转至下载链接
您好,Turbo V3无法下载,点击下载按钮会一直刷新页面,无法跳转到下载链接!
我可以正常下載,如果你無法下載可能是"civitai"的問題.
Attempting to download V3 just refreshes the page and nothing starts - anyone else got his?
Same
I can download it normally. If you can't download it, it might be a problem with "civitai".
@iamddtla yep many issues with this red site.
same
same
civtai - fixxx your siteeeeeeeeeeeeeeeeeeeeeee
me too
I can literally download all checkpoints but this one so I am not sure if it is a bigger site issue this time
Works now!
您好,Turbo V3无法下载,点击下载按钮会一直刷新页面,无法跳转到下载链接!
等待"civitai"修復錯誤吧,有些人能夠下載模型,有些人不行。我看到模型下載的次數有再增加。
@iamddtla I don't know if this is a hassle for you but maybe try a re-upload? All other models (including yours) are downloadable.
Only V3 leads to reloading the site and no download starting, so I am not sure if it really simply is an issue on CivitAI's side this time. Feels like the link itself is faulty?
我等待V3.5试试看能不能下载,谢谢大家
Works again!
@SaburoDio I had other friends help me download and test it, and they were able to download the model successfully.
@iamddtla Can confirm it is working, thank you a lot!
刚刚试了下,可以下载了~
很奇怪3.0可以下载了,3.5不行,是不是需要再等两天才可以。
可以了,3.5也可以下载了
Turbo V3 surprised me with higer quality of image and lower file size
Can't download 3.5 it just keeps refreshing the page. It did just go off of yellow buzz like 20 min ago though.
Same for me
Yeah, had the same problem another Lora earlier too
Same here, even with the API download
Its working now
def huk can i not download this? just refreshes the page.... need some of that pornmaster v3.5 porn gad damn it
dl is grayed out for me, maybe fixing it -link is back, refreshed the page, so not fixed
The previous version had the same problem.
@bigconcat @ogbtjyqat450 it's downloading now. maybe we were to early to download the lora or maybe high demand broke something
The model cannot be downloaded due to a problem with the "civitai" website; please wait for them to fix the error.
Any chance of getting v3.5 uploaded as a bf16 like the others?
Due to issues that arose after the ComfyUI update, and because my current method of creating merged models is unable to produce a bf16 version of z-image, the issue persists.
3.5太完美了,完美契合角色lora,对人体的解剖结构还原真实,不同的姿势也能完美再现,感谢作者!
期待3.5有bf16版本,感覺不能做出太複雜的動作
双采就行了,用一个动作较好的其他模型生成第一步底噪,然后用这个模型生成后面的步数
太他妈的难得了,既不像其他人的模型清一色只能出真人,保持了原始的部分风格化能力,同时又不像那些模型一样在非真人情况下会出现反生物学的难绷猫咪,我真后悔今天才用上你的模型,焯!
I have this really awesome idea. Stop posting like 800 models on CivitAI, do better descriptions and post only the best ones in various formats. O.M.G. I'm a genius.
Base is amazing and easy. Even bear can use.
Turbo worked with my character LoRAs very well, about 90% of the likeness of the character trained on the original.
But Base doesn't seem to do it at all. Perhaps it's a dataset thing or just unfixable because base's architecture?
Thanks for you work, but later version are very disappointing.
v1 make best result (even if not perfect), but, v2, v3 ou v3.5 are really awfull



















