Sync 3 new model versions from Civitai

NSFW_WAN2_2_T2V_White_lace_outfit_-_Elf_ear_accessories_-_Long_silver_hair_-White_thigh-high_socks/Wan_Video_2_2_T2V-A14B/White lace outfit Elf ear accessories Long silver hair.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:128fc1130b1e79eab761df23e05c0ada4a3e60691e81cc6e4a42a90a1b2a8fe3
+size 306807976

Penis_Lora_Blowjob_Cumshot_Taz_-_WAN_2_2_14b_5B_1_3b_T2V__I2V_Wan_2_1__2_2/Wan_Video_2_2_T2V-A14B/PENISLORA_22_HIGH_e149.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5b1fd0885073b765ff427d748c90605d5642e2105310a4593752e5385ccd87f
+size 306807976

Penis_Lora_Blowjob_Cumshot_Taz_-_WAN_2_2_14b_5B_1_3b_T2V__I2V_Wan_2_1__2_2/Wan_Video_2_2_T2V-A14B/PENISLORA_22_LOW_e93.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e645c0fef82309374f72faf53edd231dc5ff86a396621370a48a58db37916dcd
+size 306807976

README.md

@@ -313,5 +313,20 @@ A collection of models downloaded from Civitai. Click on a card to browse the fi
 <summary style="cursor: pointer; font-size: 0.9em; text-align: center; padding: 4px; border: 1px solid #d1d5db; border-radius: 6px;">View 1 More Previews</summary>
 <div style="padding-top: 8px;"><img src="https://huggingface.co/UnifiedHorusRA/TheWan2.2T2Vclass/resolve/main/680B85355D3DE68AAA09F5E3D1723881125898A9CF3EEC62B0AEC70C3E1A69B4_81c8ba61.gif" style="width: 100%; margin-top: 8px; border-radius: 4px;" /></div>
 </details></div>
+<div style="display: flex; flex-direction: column;"><a href="https://huggingface.co/UnifiedHorusRA/TheWan2.2T2V/tree/main/NSFW_WAN2_2_T2V_White_lace_outfit_-_Elf_ear_accessories_-_Long_silver_hair_-White_thigh-high_socks" style="display: block; position: relative; width: 200px; height: 250px; border-radius: 8px; overflow: hidden; text-decoration: none; color: white; background-image: url('https://huggingface.co/UnifiedHorusRA/TheWan2.2T2Vclass/resolve/main/128FC1130B1E79EAB761DF23E05C0ADA4A3E60691E81CC6E4A42A90A1B2A8FE3_7930c3e2.jpg'); background-size: cover; background-position: center; box-shadow: 0 4px 6px -1px rgba(0,0,0,0.1);">
+<div style="position: absolute; top: 0; left: 0; right: 0; bottom: 0; background: linear-gradient(to top, rgba(0,0,0,0.85) 0%, rgba(0,0,0,0) 60%); display: flex; flex-direction: column; justify-content: flex-end; padding: 12px; text-align: left;">
+<h3 style="margin: 0; font-size: 1.1em; text-shadow: 1px 1px 3px rgba(0,0,0,0.8);">NSFW WAN2.2 T2V White lace outfit - Elf ear accessories - Long silver hair -White thigh-high socks</h3>
+<p style="margin: 4px 0 0 0; font-size: 0.9em; text-shadow: 1px 1px 3px rgba(0,0,0,0.8);">Aaron_PP</p>
+</div>
+</a><details style="width: 200px; margin-top: 8px;">
+<summary style="cursor: pointer; font-size: 0.9em; text-align: center; padding: 4px; border: 1px solid #d1d5db; border-radius: 6px;">View 1 More Previews</summary>
+<div style="padding-top: 8px;"><img src="https://huggingface.co/UnifiedHorusRA/TheWan2.2T2Vclass/resolve/main/128FC1130B1E79EAB761DF23E05C0ADA4A3E60691E81CC6E4A42A90A1B2A8FE3_06b3652d.jpg" style="width: 100%; margin-top: 8px; border-radius: 4px;" /></div>
+</details></div>
+<div style="display: flex; flex-direction: column;"><a href="https://huggingface.co/UnifiedHorusRA/TheWan2.2T2V/tree/main/Penis_Lora_Blowjob_Cumshot_Taz_-_WAN_2_2_14b_5B_1_3b_T2V__I2V_Wan_2_1__2_2" style="display: block; position: relative; width: 200px; height: 250px; border-radius: 8px; overflow: hidden; text-decoration: none; color: white; background-image: url('https://huggingface.co/UnifiedHorusRA/TheWan2.2T2Vclass/resolve/main/E5B1FD0885073B765FF427D748C90605D5642E2105310A4593752E5385CCD87F_22ec8ede.gif'); background-size: cover; background-position: center; box-shadow: 0 4px 6px -1px rgba(0,0,0,0.1);">
+<div style="position: absolute; top: 0; left: 0; right: 0; bottom: 0; background: linear-gradient(to top, rgba(0,0,0,0.85) 0%, rgba(0,0,0,0) 60%); display: flex; flex-direction: column; justify-content: flex-end; padding: 12px; text-align: left;">
+<h3 style="margin: 0; font-size: 1.1em; text-shadow: 1px 1px 3px rgba(0,0,0,0.8);">Penis Lora (+Blowjob, +Cumshot) [Taz]  - WAN 2.2 14b / 5B / 1.3b T2V & I2V (Wan 2.1 & 2.2)</h3>
+<p style="margin: 4px 0 0 0; font-size: 0.9em; text-shadow: 1px 1px 3px rgba(0,0,0,0.8);">tazmannner379</p>
+</div>
+</a></div>
 <!--CIVITAI_MODEL_GALLERY_END-->
 </div>

Wan_Video_2_2_T2V-A14B_info.md

@@ -3624,4 +3624,199 @@ As always, please use responsively
 *   **Size**: 585.10 MB
 *   **Hash (AutoV2)**: `2A8B9A6745`
 *   **Hash (SHA256)**: `2A8B9A67454C91C0203826891CA952408F9563CEEDE22CD0F32B9BA939ADD70A`
+---
+
+---
+# NSFW WAN2.2 T2V White lace outfit - Elf ear accessories - Long silver hair -White thigh-high socks (Version: v1.0)
+**Creator**: [Aaron_PP](https://civitai.com/user/Aaron_PP)
+**Type**: LORA
+**Base Model**: Wan Video 2.2 T2V-A14B
+**Version Uploaded**: 2025-10-06
+**Trigger Words**: `NSFBSLT`
+**Civitai Model ID**: 2019716
+**Civitai Version ID**: 2285909
+**Stats (at time of fetch for this version)**:
+*   Downloads: 34
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## 📄 Description (Parent Model)
+Style
+Using this Lora will generate a fixed NSFW content！ 🎬✨
+Suitable for wan2.2 T2V 14B low-noise model This is a model based on a large amount of material with a specific style. It generates NSFW content.
+### Character Description:
+-
+Hair
+: She has long silver-white hair, which flows smoothly over her shoulders, appearing very graceful. -
+Makeup
+: Her makeup is delicate, with light blue eye shadow on her eyes, thick lashes, and a light pink lipstick on her lips, giving a fresh and natural look.
+-
+Ears
+: She is wearing a pair of intricate elf ear accessories, with pink decorations that add a dreamy feel.
+### Outfit Description:
+-
+Top
+: She is wearing a white lace top with complex embroidery and decorations, making it very luxurious. The neckline is low, revealing part of her collarbone and shoulders, adding a sensual element.
+-
+Skirt
+: Her skirt is also white, with a full, voluminous hem decorated with lace and feathers, giving it a dreamy and romantic appearance.
+-
+Socks
+: She is wearing a pair of white thigh-high socks with lace trim, enhancing the overall delicacy.
+Trigger word：NSFBSLT
+This is based on WAN2.2 T2V low noise model training and is used first for low noise model， Different loras have different model weights and clip weights. Some lora adjustments may not work if not adjusted properly. It is recommended to search for my online model and lora adjustment to ensure that it can take full effect. Click the link below to experience it online
+There are many NSFW models I uploaded, you can choose any one
+🔗
+click here
+Comfyui Free trial!!!
+🎉
+Use It on RunningHub
+No extra nodes to install
+Works seamlessly with 4090 (48G VRAM) and similar setups
+Pre-tuned parameters: start using it right away
+Register and you will receive 1000 points. Log in every day and you will receive extra points.
+🔗
+click here
+Generate hundreds of videos in the following way:
+No need to download various nodes or adjust various complex parameters
+Register now to get 1,000 RH points and 100 daily reward points!!!
+LoRA Online demo
+：
+🔗
+click here
+Try the workflow immediately🎉
+Click the link to test and explore parameter Settings without payment. Just register for free.
+## Civitai Links
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/2019716?modelVersionId=2285909)**
+*   [View Full Model Page →](https://civitai.com/models/2019716)
+*   [View Creator Profile →](https://civitai.com/user/Aaron_PP)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `White lace outfit Elf ear accessories Long silver hair.safetensors`
+*   **Size**: 292.59 MB
+*   **Hash (AutoV2)**: `128FC1130B`
+*   **Hash (SHA256)**: `128FC1130B1E79EAB761DF23E05C0ADA4A3E60691E81CC6E4A42A90A1B2A8FE3`
+---
+
+---
+# Penis Lora (+Blowjob, +Cumshot) [Taz]  - WAN 2.2 14b / 5B / 1.3b T2V & I2V (Wan 2.1 & 2.2) (Version: Wan 2.2 14B T2V - HIGH-V1)
+**Creator**: [tazmannner379](https://civitai.com/user/tazmannner379)
+**Type**: LORA
+**Base Model**: Wan Video 2.2 T2V-A14B
+**Version Uploaded**: 2025-09-30
+**Trigger Words**: `N/A`
+**Civitai Model ID**: 1476909
+**Civitai Version ID**: 2267701
+**Stats (at time of fetch for this version)**:
+*   Downloads: 1401
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## 📄 Description (Parent Model)
+About this version
+I trained using the newly re-captioned dataset from the 5B model. The result is incredibly good. For the first time I'm pretty happy with the result. Give it a try.  Most examples are with lightning speed lora and low resolution (480x832). I also released an I2V version. Try using the t2v at 0.5 str + the i2v lora at 1 str for i2v.
+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.
+## Civitai Links
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1476909?modelVersionId=2267701)**
+*   [View Full Model Page →](https://civitai.com/models/1476909)
+*   [View Creator Profile →](https://civitai.com/user/tazmannner379)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `PENISLORA_22_HIGH_e149.safetensors`
+*   **Size**: 292.59 MB
+*   **Hash (AutoV2)**: `E5B1FD0885`
+*   **Hash (SHA256)**: `E5B1FD0885073B765FF427D748C90605D5642E2105310A4593752E5385CCD87F`
+---
+
+---
+# Penis Lora (+Blowjob, +Cumshot) [Taz]  - WAN 2.2 14b / 5B / 1.3b T2V & I2V (Wan 2.1 & 2.2) (Version: Wan 2.2 14B T2V - LOW-V1)
+**Creator**: [tazmannner379](https://civitai.com/user/tazmannner379)
+**Type**: LORA
+**Base Model**: Wan Video 2.2 T2V-A14B
+**Version Uploaded**: 2025-09-30
+**Trigger Words**: `PENISLORA`
+**Civitai Model ID**: 1476909
+**Civitai Version ID**: 2267675
+**Stats (at time of fetch for this version)**:
+*   Downloads: 1537
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## 📄 Description (Parent Model)
+About this version
+I trained using the newly re-captioned dataset from the 5B model. The result is incredibly good. For the first time I'm pretty happy with the result. Give it a try.  Most examples are with lightning speed lora and low resolution (480x832). I also released an I2V version. Try using the t2v at 0.5 str + the i2v lora at 1 str for i2v.
+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.
+## Civitai Links
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1476909?modelVersionId=2267675)**
+*   [View Full Model Page →](https://civitai.com/models/1476909)
+*   [View Creator Profile →](https://civitai.com/user/tazmannner379)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `PENISLORA_22_LOW_e93.safetensors`
+*   **Size**: 292.59 MB
+*   **Hash (AutoV2)**: `E645C0FEF8`
+*   **Hash (SHA256)**: `E645C0FEF82309374F72FAF53EDD231DC5FF86A396621370A48A58DB37916DCD`
 ---

civitai_tracker.json

@@ -280,6 +280,19 @@
         "2287208",
         "2287197"
       ]
+    },
+    "2019716": {
+      "name": "NSFW WAN2.2 T2V White lace outfit - Elf ear accessories - Long silver hair -White thigh-high socks",
+      "versions": [
+        "2285909"
+      ]
+    },
+    "1476909": {
+      "name": "Penis Lora (+Blowjob, +Cumshot) [Taz]  - WAN 2.2 14b / 5B / 1.3b T2V & I2V (Wan 2.1 & 2.2)",
+      "versions": [
+        "2267701",
+        "2267675"
+      ]
     }
   },
   "versions": [
@@ -373,6 +386,9 @@
     "2285508",
     "2287248",
     "2287208",
-    "2287197"
+    "2287197",
+    "2285909",
+    "2267701",
+    "2267675"
   ]
 }