模型介紹為中英雙語，中文使用者可以關閉翻譯。
中國用戶無法購買buzz的人可至淘寶找civitai代儲。
PornMaster Krea2 Turbo T2I Workflow
PornMaster Krea2 Uncensored lora
Krea 2 styles: ComfyUI-NO8D-controls
如果我沒有發布的模型格式，你可以自行使用"GGUFY"來進行量化.
如果某些被強力審查生成不出來的主題可以搭"Krea2 TextFusion Refusal-Reduction LoRA"一起使用，也許能夠生成。
官方原版的krea 2 turbo模型在描述某些臉部特徵或攝影風格的提示詞時，會將人物變成2d或半寫實風格，可透過"Realism slider lora"來改善.
"Realism slider lora"可以將動漫角色的lora變成寫實風格.
我已經在我自己訓練的角色lora上進行測試，可以良好的還原人物樣貌並且生成nsfw的內容。
Krea2模型使用英文提示詞來生成圖片的精準度會比使用其他語言更高。
Krea2模型如果使用中文提示詞時，人物會自動更偏向亞洲面孔。
有時會在不需要出現精液的情況中，生成的圖片會自動包含了精液，使用”krea2 raw”的工作流，即可填寫負面提示詞，並將cfg設定為1.5，負面提示詞即可生效。
你也可在負面提示詞排除：(cum, White sweat, white water, white liquid, semen:1.4).
2d、Anime.
也可使用"Transforms into water Slider lora"將精液轉化為水。
可以使用-1權重的"wetness-slider-krea2 lora"來去除水和精液。
If I haven't released the model format, you can use "GGUFY" for quantization yourself.
If some themes that cannot be generated due to strong censorship can be used together with "Krea2 TextFusion Refusal-Reduction LoRA", they may be able to be generated.
The official Krea 2 Turbo model will turn the character into a 2D or semi-realistic style when describing certain facial features or photographic style prompts. This can be improved using the "Realism slider lora".
"Realism slider lora" can transform the anime character Lora into a realistic style.
I have tested it on my own trained character, Lora, and it can reproduce the character's appearance well and generate NSFW content.
The Krea2 model generates images more accurately when using English prompts than when using prompts in other languages.
When the Krea2 model is given prompts in Chinese, the generated people will automatically tend to have more Asian facial features.
Sometimes, images may automatically include semen even when it is not intended. If this happens, use the "krea2 raw" workflow, where you can enter a negative prompt and set the CFG value to 1.5. This will make the negative prompt take effect.
You can also exclude it by negative prompts: (cum, White sweat, white water, white liquid, semen:1.4).
2D, Anime.
You can also use "Transforms into water Slider lora" to convert semen into water.
You can use "wetness-slider-krea2 lora" with a weight of -1 to remove water and semen.
text_encoders
qwen3vl_4b_int8_convrot.safetensors
vae
我的其他檢查站和Lora。
My other checkpoints and Lora.
--
我已將模型上傳至runninghub。
I have uploaded the model to runninghub.
Pornmaster_krea2_turbo_fp8_v1
https://www.runninghub.ai/model/public/2070906642396434434/?inviteCode=rh-v1304
Pornmaster_krea2_turbo_fp8_v2
https://www.runninghub.ai/model/public/2070906642396434434/?inviteCode=rh-v1304
Pornmaster_krea2_Turbo_int8_convrot_v2
https://www.runninghub.ai/model/public/2075976521210408961/?inviteCode=rh-v1304
Pornmaster_krea2_Turbo_bf16_v2
https://www.runninghub.ai/model/public/2078120164255870977/?inviteCode=rh-v1304
Pornmaster_krea2_Turbo_fp8_v2.5
https://www.runninghub.ai/model/public/2070906642396434434/?inviteCode=rh-v1304
Pornmaster_krea2_Turbo_int8_convrot_v2.5
https://www.runninghub.ai/model/public/2075976521210408961/?inviteCode=rh-v1304
Pornmaster_krea2_Turbo_bf16_v2.5
https://www.runninghub.ai/model/public/2078120164255870977/?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
int8_convrot & fp8 & bf16:
V2.5版本提示詞反應更精準，並減少對KREA2官方模型原始風格的影響。
V2.5版本與V1、V2有極大的差別，如果你複製前面版本的提示詞在V2.5版本使用，某些圖片可能會出錯，必須重新編寫提示詞與提示詞的權重。
將精液的培訓照片數量減少，減少在不需要出現精液時卻生成精液的情況。
改善了陰莖與觸手錯亂的情況。
良好的保留KREA2官方模型原本內建的角色。
與角色LORA相容性良好。
優化了背景。
要避免生成精液可以在負面提示詞添加: (cum, White sweat, white water, white liquid, semen:1.4).
V2.5 offers more accurate prompt interpretation while reducing its impact on the original style of the official KREA2 base model.
V2.5 is significantly different from V1 and V2. If you reuse prompts from previous versions with V2.5, some images may produce incorrect results. You will need to rewrite your prompts and adjust their prompt weights.
Reduced the number of training images containing semen, minimizing cases where semen is generated when it is not intended.
Improved issues where the penis and tentacles were confused or incorrectly generated.
Better preserves the official KREA2 model's original built-in characters.
Good compatibility with character LoRAs.
Optimized background generation.
To avoid generating semen, add the following to your negative prompt:
(cum, White sweat, white water, white liquid, semen:1.4)
text_encoders
qwen3vl_4b_int8_convrot.safetensors
vae