Upload 1476909/2456935/README.md with huggingface_hub

1476909/2456935/README.md

@@ -1,17 +1,18 @@
 ---
 license: other
 tags:
+- style
 ---
 
-# Unknown - 2456935
+# Penis Lora (+Blowjob, +Cumshot) [Taz]  - WAN 2.2 14b / 5B / 1.3b T2V & I2V (Wan 2.1 & 2.2) + Qwen + Zimage Turbo-ZImage Turbo V1 - 2456935
 
-**Model Type**: Unknown
+**Model Type**: LORA
 
-**Base Model**: Unknown
+**Base Model**: ZImageTurbo
 
 **Trigger Words**: None
 
-**Tags**: None
+**Tags**: style
 
 ## Gallery
 
@@ -35,14 +36,75 @@ tags:
 
 ## Description
 
-No description available.
+About this version (qwen v2)
+
+A brushup of the dataset, with better result than V1 for qwen. I will use the same dataset again for zturbo when the base model is released.
+
+**Trigger word:** PENISLORA
+
+**What can this lora do?**
+
+This lora can add erect penises to both men or women viewed from the front/side. Other angles such as POV may have a backwards penis head.
+
+Other things it can now do:  
+Side view of the penis
+
+Cumming / Cumshots
+
+Blowjobs (its captioned for the words "blowjob" and "deepthroat" )
+
+What can't it do?
+
+No penetration in the training data. Also nothing from POV angle, though there is a few images from above and 1 POV video in the training data.
+
+Sometimes blowjobs with cumming have the penis slip out the closed mouth.
+
+**Recommended Settings**
+
+It works pretty good with the new lightning dyno high model. I'll link to it in my example workflow. I like to use dyno high model (no lightning lora), then for low I use the lightning v2 lora on the regular 2.2 low base model.
+
+**Dataset**
+
+84 images at 512x resolution
+
+43 videos at 256x resolution
+
+(I let DP pick the aspect ratio automatically)
+
+This is the same exact dataset as the 2.2 5B model. I made no changes.
+
+**Training**
+
+I used the default diffusion pipe settings.
+
+[optimizer]
+
+type = 'adamw\_optimi'
+
+lr = 2e-5
+
+betas = [0.9, 0.99]
+
+weight\_decay = 0.01
+
+eps = 1e-8
+
+I was baffled why it was taking so long to train the high until I realized after over 60 hours of training that I had put my videos in the images directory which resulted in the high being trained ONLY only on videos and twice (once with a very high resolution). Once I fixed this, I went back and trained from 11K steps up to around 13K with the images in the training data. The high model was fine without to be honest.
+
+For the low, I trained it properly with videos and images the whole way, around 6K steps in I upped the image resolution from 512 to 1024 actually and didn't get an OOM (it fit around 24GB exactly). I trained it to around 10.5K steps. Also I trained the low on the full timestep range (0 to 1 instead of 0 to 0.85) from some advice, it may switch better over from high to low on the speed up lora with low steps.
+
+I think I might do another version with more angles such as POV and from the behind to make this work for any situation. In that case I don't think it needs 10K steps per training session, epochs around 5K steps looked fine.
+
+**The results**
+
+I think it was a combination of improved captioning and 2.2 base model being better. But this lora turned out really well.
 
 ---
 
-Author: [Unknown](https://civitai.com/user/Unknown)
+Author: [tazmannner379](https://civitai.com/user/tazmannner379)
 
 Model: [CivitAI Model Page](https://civitai.com/models/1476909?modelVersionId=2456935)
 
 Archive: [CivArchive Page](https://civarchive.com/models/1476909?modelVersionId=2456935)
 
-<!-- Version: 20260422_v4_update -->
+<!-- Version: single_readme_update -->