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
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。
這是一個測試版本，不要對它有太高的期待，nsfw的姿勢和性器官有些微改進，如果性器官要像SDXL版本那樣良好，還有一段很長的路要走。
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。
如果對生成的性器官不滿意請使用PornMaster SDXL系列的Inpainting 檢查站來修復性器官。
如果原版z-image Turbo中內建的人物面孔還原的不好時，可以透過我的工作流將面部修復中使用的檢查站替換成原版z-image Turbo，但是低於24 GB VRAM時不建議這麼做，生成圖片所需的時間將會延長非常多。
--
When using nsfw's LoRa, the LoRa weights start at 0.1 and are then gradually increased to adjust the weights.
This is a test version, so don't have too high expectations. The positions and genitals in nsfw have been slightly improved, but there is still a long way to go before the genitals are as good as the SDXL version.
Increasing the resolution of the photo can increase the success rate of generating good-looking penises and genitals.
If you are not satisfied with the generated sex organs, please use the Inpainting checkpoint of the PornMaster SDXL series to repair them.
If the built-in facial reconstruction in the original z-image Turbo is not good, you can replace the checkpoint used in facial retouching with the original z-image Turbo through my workflow. However, it is not recommended to do this if you have less than 24 GB of VRAM, as it will significantly increase the time required to generate the image.
FAQ
Comments (26)
WE ARE SO CLOSE GUYS , JUST A LITTLE MORE JUST A LITTLE MORE
almost there...
f8 please cuda outof memory
We need a distilled version so the plebs can generate as well. Love your models and rolas!
https://huggingface.co/qpqpqpqpqpqp/Z_Image_fp8/blob/main/masterZImage_turboV01_fp8.safetensors
Someone else has already created an FP8 version for me; you can download it here.
Так есть же дистилированная турбо версия. В AI-Toolkit есть опция.
@Iggort @windkazuya333264 dedistilled*
Thanks to @qek for helping me create the FP8 version, which has been uploaded.
Yeah, Nah. Every released ZIT model is still hopeless for NSFW and just can't do cocks and pussies correctly - you need to get super lucky just to get 1 looking ok(ish) in 100 gens. Also messes up when used with character Lora and diminishes the realistic look of ZIT. I've now wasted 10K buzz optimistically downloading various promised NSFW capable ZIT checkpoints, but the reality is that until the Base is released (IF that ever happens), it's pointless to keep trying.
If you are not satisfied with the generated sex organs, please use the Inpainting checkpoint of the PornMaster SDXL series to repair them.
@iamddtla can you share a workflow please?
Please don't be discouraged. The Z model itself is an accelerated version, which inevitably causes problems with LORA. It is indeed difficult to generate a perfect image in one go, and the lottery is the most patience-consuming process. Please pray for the release of the original Z model.
Furthermore, complaining to private creators is pointless. Besides, they need to rent higher-end graphics cards to create Lora or fusion models for free, and they release them for everyone to use for free, so we should be grateful.
另：打完飞机进入贤者模式，再来浏览C站会让自己清醒很多~
I'm running the bf16 version of this checkpoint locally with forge neo on my RTX 3060 12GB. In that regard it isn't costing me any buzz to play around with it. What I'm noticing is that not all of the images generated are great. Some indeed are downright terrible, I'd say maybe 2-3 out of 10 are good with 1 out of 20 or so being really good. The prompt seems to really play into it as well. If you're using any LoRAs, some LoRAs play well with this checkpoint, some don't seem to get along with it at all regardless of strength.
When it comes to NSFW content I do think this checkpoint is well ahead of most of the other ones out. There's some room for improvement, as with anything but it is ahead of most.
The 2nd pass ruins private parts it merges penis and vagina together, Is there a solution to that? like in your workflow you either do not use 2nd pass or use it with 1.2x upscale, does that mean it ruins it because of high resolution or, it gets ruined because of the 2nd pass.
@iamddtla It makes the image very blurry looking.
@Luten If you simply need a function to zoom in on images, I will release a simple workflow for zooming in on images at 4x magnification later. Enlarge the latent space; avoid using too low a desion value, as I forgot that this would make the image blurry. If you are using a low value for the "desion" setting, you can try increasing the number of steps in "Enlarge the latent space".
@iamddtla By blurry I mean something like this https://civitai.com/posts/25707920 , with the denoise value of .2 in the 2nd pass
@Luten This function is similar to generating images from images; it's best to set the "denoise" value to 0.5 or higher.
This. Works! for anime too, you heard it here first folks!
Great work! By the way, have you considered developing a workflow for converting Anime to Realistic Style directly using PornMaster-Z-image? That would be incredibly awesome!
@iamddtla 谢谢大佬