已經可以使用"綠色buzz"購買我的lora了，要用綠色buzz去購買我的其他lora時，只需將每個lora網址中的".red'替換成".com"，如果我的某些lora因為系統問題，無法用綠色buzz購買時，請私下聯絡我。
You can now use Green Buzz to purchase my LoRAs!
To purchase my other LoRAs using Green Buzz, simply replace ".red" with ".com" in each LoRA's URL.
If you're unable to purchase any of my LoRAs using Green Buzz due to a system issue, please contact me privately.
我對檢查站的設計理念:
只針對生殖器和NSFW增強，但是盡可能的不影響官方預設的風格、人臉。
與LORA的相容性必須良好。
My Design Philosophy for the Checkpoint:
Enhance only genitalia and NSFW-related features while minimizing any impact on the official default style and facial features.
Must maintain excellent compatibility with LoRAs.
如果你要使用人物lora，在BASE版本上效果會更好。
moss image的負面提示詞非常有效果，請善用負面提示詞。
If you are using character LoRAs, they will perform better with the BASE version.
Moss Image's negative prompts are very effective. Make good use of them.
PornMaster Moss de-SFT Slider
PornMaster Moss SFT t2i workflow
PornMaster MOSS Image Prompt Skill
MOSS-Image User Guide
MOSS-Image 用戶指南
MOSS-Image 支援自然語言、Tag 字串以及 JSON Layout 等多種輸入格式.
MOSS-Image supports multiple input formats, including natural language, tag sequences, and JSON layouts.
text_encoders:
qwen3.5_9b_int8_convrot or qwen3.5_9b_bf16
vae:
My other checkpoints and Lora.
我已將模型上傳至runninghub。
I have uploaded the model to runninghub.
PornMaster_Moss_SFT_int8_convrot
https://www.runninghub.ai/zh-cn/model/public/2111739599463067650/?inviteCode=rh-v1304
PornMaster_Moss_Base_int8_convrot
https://www.runninghub.ai/zh-cn/model/public/2116797220992385026/?inviteCode=rh-v1304
PornMaster_Moss_MIX_int8_convrot
https://www.runninghub.ai/zh-cn/model/public/2119299468490268673/?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
此版本為int8_convrot格式。
v2版本:
為了避免訓練過度，從訓練的素材中移除了moss image原本已經學會的概念，並增加新的nsfw訓練素材，也降低了對攝影風格的影響。
為了與女性生殖器lora具有良好相容性，女性生殖器沒有綁定特定的形狀。
This version uses the int8_convrot format.
v2 Version:
To prevent overtraining, concepts that MOSS Image had already learned were removed from the training dataset. New NSFW training materials were added, and the influence of photographic styles was also reduced.
To ensure good compatibility with female genitalia LoRAs, no specific shape was assigned to the female genitalia.
FAQ
Comments (22)
Something that would be appreciated, is a DMD version.
What is the difference in V2, bigger holes only?
About this version<<
大佬moss相比krea2有什么优势吗
把這個問題問ai就會有答案.
感觉细节质感之类的不如k2 而且这2个模型量级差太多了
更小的体积，更好的提示词遵循度，无清洗的数据集原生就能nsfw，支持中文，支持bbox，前面那个兄弟说细节质感不如kr2纯粹是提示词没写好
提示詞懂得很多，連人體豬肉攤或烤人這種鬼東西都不用借助LoRa就可以生出來
need fp8
13k yellow to download.
let me guess, civitai does not offer the option to ask for a kidney or leg?
should at least have the option for soul of the firstborn or something like that.
I just logged-in to SeaArt just to buy the model, but the whole freaking site is in Chinese and the English version is terrible bad. On top of that, I don't see a "buy" button. The Download button requires subscription. Like there is no "one pay" option.
SeaArt's user interface is really bad; it took me a long time to find the "download" option. Its download button is hidden in the pattern of three small dots above.
If it's inconvenient for you to buy yellow Buzz on Civitai, you can buy green Buzz instead and then contact me to exchange it for yellow Buzz.
@iamddtla Tensor上的没有了吗
@xiaoshidi123 Tensor很爛，他們故障也不修復，而且我要販賣lora，光是krea2申請了三個月他們公司說沒時間處理，而且還欠了許多創作者錢，那邊我暫時只能當作模型防盜而上傳去那。 如果妳在中國需要購買我的模型就到我的SeaArt帳號吧。
civitai又bug了？V2下不动😓
May I ask what's the difference between V1 and V2? V1 is powerful enough. If V2 can do further, I won't be hesitated to pay for that. lol
Please see: About this version <<<
可以和其他的小穴lora更好的兼容
I get the error
# ComfyUI Error Report ## Error Details - Node ID: 13 - Node Type: CLIPTextEncode - Exception Type: NotImplementedError - Exception Message: NotImplementedError: Cannot copy out of meta tensor; no data!
When trying to use your workflow, an this checkpoint. Any tips?