<h3>模型介紹為中英雙語，中文使用者可以關閉翻譯。</h3>Trubo:<a target="_blank" rel="ugc" href="https://civarchive.com/models/2199345?modelVersionId=2476326">Pornmaster Z Image Turbo Workflow</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/2281505?modelVersionId=2567807">Pornmaster Z Image Turbo Controlnet Workflow</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/2259985?modelVersionId=2544039">PornMaster Z-image-turbo Controlnet: Cosplay - Anime to Realistic Style</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/2284667?modelVersionId=2571287">PornMaster Z-image Increase realism &amp; detail &amp; sharpness</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/2302722?modelVersionId=2591008">Pornmaster Z-Image Turbo i2i Workflow</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/2287697/pornmaster-simple-4x-magnification-workflow?modelVersionId=2574505">PornMaster Simple 4X Magnification Workflow</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/2333662?modelVersionId=2625066">Pornmaster Z-Image Turbo T2I Workflow-Double checkpoints &amp; realism enhancer</a>--Base:<a target="_blank" rel="ugc" href="https://civarchive.com/models/2386331?modelVersionId=2683352">Pornmaster Z Image Base t2i Workflow</a><h3>--</h3><a target="_blank" rel="ugc" href="https://github.com/shootthesound/comfyUI-Realtime-Lora">comfyUI-Realtime-Lora</a><a target="_blank" rel="ugc" href="https://github.com/Haoming02/sd-webui-forge-classic/tree/neo?tab=readme-ov-file">Stable Diffusion WebUI Forge - Neo</a>--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。<h3 id=":lora">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。</h3>如果對生成的性器官不滿意請使用<a target="_blank" rel="ugc" href="https://civarchive.com/models/82543?modelVersionId=2574712">PornMaster SDXL</a> 或<a target="_blank" rel="ugc" href="https://civarchive.com/models/2382648">PornMaster flux2 klein 9b base </a>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.<h3 id="note:-some-people's-character-lora-training-works-while-others'-does-not-i-don't-know-why.">Note: Some people's character lora training works, while others' does not; I don't know why.</h3>If you are not satisfied with the generated sex organs, please use the Inpainting checkpoint of <a target="_blank" rel="ugc" href="https://civarchive.com/models/82543?modelVersionId=2574712">PornMaster SDXL</a> or <a target="_blank" rel="ugc" href="https://civarchive.com/models/2382648">PornMaster flux2 klein 9b base</a> to repair the sex organs.--Clip: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/z_image_turbo/blob/main/split_files/text_encoders/qwen_3_4b.safetensors">qwen_3_4b.safetensors</a>Vae: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/z_image_turbo/blob/main/split_files/vae/ae.safetensors">ae.safetensors</a>--<h2 id="runninghub">我已將模型上傳至<a target="_blank" rel="ugc" href="https://www.runninghub.ai/user-center/1968577612886994945/model?inviteCode=rh-v1304">runninghub</a>。</h2><h3 id="i-have-uploaded-the-model-to-runninghub.">I have uploaded the model to <a target="_blank" rel="ugc" href="https://www.runninghub.ai/user-center/1968577612886994945/model?inviteCode=rh-v1304">runninghub</a>.</h3>PornMaster z-image Turbo V0.1_fp8:<a target="_blank" rel="ugc" href="https://www.runninghub.ai/model/public/2012876652145020930/?inviteCode=rh-v1304">https://www.runninghub.ai/model/public/2012876652145020930/?inviteCode=rh-v1304</a>PornMaster z-image Turbo V0.1_bf16:<a target="_blank" rel="ugc" href="https://www.runninghub.ai/model/public/2012891520348725249/?inviteCode=rh-v1304">https://www.runninghub.ai/model/public/2012891520348725249/?inviteCode=rh-v1304</a>PornMaster z-image Turbo V0.2_fp8:<a target="_blank" rel="ugc" href="https://www.runninghub.ai/model/public/2012870272323424257/?inviteCode=rh-v1304">https://www.runninghub.ai/model/public/2012870272323424257/?inviteCode=rh-v1304</a>PornMaster z-image Turbo V0.2_bf16:<a target="_blank" rel="ugc" href="https://www.runninghub.ai/model/public/2012858316384374786/?inviteCode=rh-v1304">https://www.runninghub.ai/model/public/2012858316384374786/?inviteCode=rh-v1304</a>PornMaster z-image Turbo V1_fp8:<a target="_blank" rel="ugc" href="https://www.runninghub.ai/model/public/2015385918403780610/?inviteCode=rh-v1304">https://www.runninghub.ai/model/public/2015385918403780610/?inviteCode=rh-v1304</a>PornMaster z-image Turbo V1_bf16:<a target="_blank" rel="ugc" href="https://www.runninghub.ai/model/public/2015380234719207425/?inviteCode=rh-v1304">https://www.runninghub.ai/model/public/2015380234719207425/?inviteCode=rh-v1304</a>PornMaster z-image Turbo V2_fp8:<a target="_blank" rel="ugc" href="https://www.runninghub.ai/model/public/2023636060722434049/?inviteCode=rh-v1304">https://www.runninghub.ai/model/public/2023636060722434049/?inviteCode=rh-v1304</a>PornMaster z-image Turbo V2_bf16<a target="_blank" rel="ugc" href="https://www.runninghub.ai/model/public/2023630811089604610/?inviteCode=rh-v1304">https://www.runninghub.ai/model/public/2023630811089604610/?inviteCode=rh-v1304</a>PornMaster_z-image_base_V0.1_fp8:<a target="_blank" rel="ugc" href="https://www.runninghub.ai/model/public/2024107278651105282/?inviteCode=rh-v1304">https://www.runninghub.ai/model/public/2024107278651105282/?inviteCode=rh-v1304</a>PornMaster_z-image_base_V0.1_bf16:<a target="_blank" rel="ugc" href="https://www.runninghub.ai/model/public/2024107273051709442/?inviteCode=rh-v1304">https://www.runninghub.ai/model/public/2024107273051709442/?inviteCode=rh-v1304</a>PornMaster_z-image_base_V0.1_distilled_fp8<a target="_blank" rel="ugc" href="https://www.runninghub.ai/model/public/2025833520878325762/?inviteCode=rh-v1304">https://www.runninghub.ai/model/public/2025833520878325762/?inviteCode=rh-v1304</a>PornMaster_z-image_base_V0.1_distilled_bf16<a target="_blank" rel="ugc" href="https://www.runninghub.ai/model/public/2025836003751108609/?inviteCode=rh-v1304">https://www.runninghub.ai/model/public/2025836003751108609/?inviteCode=rh-v1304</a>PornMaster z-image Turbo_5steps_V1_fp8<a target="_blank" rel="ugc" href="https://www.runninghub.ai/model/public/2026332244041801729/?inviteCode=rh-v1304">https://www.runninghub.ai/model/public/2026332244041801729/?inviteCode=rh-v1304</a>PornMaster z-image Turbo_5steps_V1_bf16<a target="_blank" rel="ugc" href="https://www.runninghub.ai/model/public/2026340550038786050/?inviteCode=rh-v1304">https://www.runninghub.ai/model/public/2026340550038786050/?inviteCode=rh-v1304</a>PornMaster z-image Turbo V3_fp8<a target="_blank" rel="ugc" href="https://www.runninghub.ai/model/public/2040397408881876993/?inviteCode=rh-v1304">https://www.runninghub.ai/model/public/2040397408881876993/?inviteCode=rh-v1304</a>PornMaster z-image Turbo V3.5_fp8<a target="_blank" rel="ugc" href="https://www.runninghub.ai/model/public/2041355991928807426/?inviteCode=rh-v1304">https://www.runninghub.ai/model/public/2041355991928807426/?inviteCode=rh-v1304</a>PornMaster z-image Turbo V3.5_fp16<a target="_blank" rel="ugc" href="https://www.runninghub.ai/model/public/2049373402028318721/?inviteCode=rh-v1304">https://www.runninghub.ai/model/public/2049373402028318721/?inviteCode=rh-v1304</a>--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: @iamddtla0620My WeChat ID: iamddtlaMy Line ID: iamddtlaTime is precious, please state your intention directly, for example: customized LORA.

PornMaster-色情大师 Z-image

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<a target="_blank" rel="ugc" href="https://civitai.com/models/82543?modelVersionId=2146693">PornMaster SDXL</a>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 <a target="_blank" rel="ugc" href="https://civitai.com/models/82543?modelVersionId=2146693">PornMaster SDXL</a> 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.

Files with SHA256: f7297f51a8d447f9d7aa90cfd86192a9c644e08aa9b6a4196b4b14d46507f6b2