所有範例圖片皆由AI生成。
All example images are generated by AI.
Download PornMaster [Flux.2 Klein 9B]
下載Lora Manager.
Download Lora Manager.
可以將Lora Manager替換成"Power Lora Loader (rgthree)".
You can replace Lora Manager with "Power Lora Loader (rgthree)".
--
範例中使用的LORA:
--
LORA used in the example:
--
使用英文提示詞的精準度會更高。
Using English prompts will result in higher accuracy.
--
text_encoders
· qwen_3_8b_fp8mixed.safetensors
vae
· or full_encoder_small_decoder.safetensors
--
我已將模型上傳至runninghub。
I have uploaded the model to runninghub.
PornMaster_flux2_klein_9b_base_fp8_V1
https://www.runninghub.ai/model/public/2030515890512465922/?inviteCode=rh-v1304
PornMaster_flux2_klein_9b_base_fp8_V2
https://www.runninghub.ai/model/public/2030515880504856577/?inviteCode=rh-v1304
PornMaster_flux2_klein_9b_base_bf16_V3
https://www.runninghub.ai/model/public/2031377858077138946/?inviteCode=rh-v1304
PornMaster_flux2_klein_9b_base_fp8_V3
https://www.runninghub.ai/model/public/2031653325136990209/?inviteCode=rh-v1304
PornMaster_flux2_klein_9b_base_fp8_V4
https://www.runninghub.ai/model/public/2054800384882946049/?inviteCode=rh-v1304
PornMaster_flux2_klein_9b_turbo_fp8_V4
https://www.runninghub.ai/model/public/2058566472678600706/?inviteCode=rh-v1304
--
我的其他檢查站和Lora。
My other checkpoints and Lora.
--
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
Download PornMaster [Flux.2 Klein 9B]
下載Lora Manager.
Download Lora Manager.
--
使用英文提示詞的精準度會更高。
Using English prompts will result in higher accuracy.
--
text_encoders
· qwen_3_8b_fp8mixed.safetensors
vae
FAQ
Comments (5)
What's the difference between automatic and manual?
The image dimensions need to be entered manually or automatically scaled.
just add a image size node and connect it to Empty Latent Image. works fine
this absolute great WF, i try and error with this wf so good, fast understanding
I love your models and WF! Even though I've been dabbling with AI image generation since the days of SD1 back in 2022, I'm still a total noob, but this is the first NSFW model that works great for me out of the box with great consistency! I have a quesion though. As understand, the base model requires 50 steps and the turbo one requires 4. Why do I see that your images were infered with 4 steps instead of 50 in the examples of the base model and workflow? Should I even use the base model to generate anything, or is it best used to only train a LORA, which I plan to do with a character.