Upload 10 files

M/Magic_Wand_Vibrator_(self-other)_(Hunyuan-Wan)/WanMagicWand.md

@@ -0,0 +1,41 @@
+# Magic Wand Vibrator (self/other) (Hunyuan/Wan) (Version: v2.0 Wan)
+
+**Creator**: [blyss](https://civitai.com/user/blyss)
+**Type**: LORA
+**Base Model**: Wan Video 14B t2v
+**Version Uploaded**: 2025-05-18
+**Trigger Words**: `using a {corded/cordless} {white/black/purple/pink/blue} MgcWndVb to stimulate her vagina, {wide shot/medium shot/medium close up/close up}`
+
+**Civitai Model ID**: 1314924
+**Civitai Version ID**: 1804710
+
+**Stats (at time of fetch for this version)**:
+*   Downloads: 1000
+*   Rating: 0 (0 ratings)
+*   Favorites: N/A
+
+---
+
+## 📄 Description (Parent Model)
+
+~Magic Wand for HunyuanVideo(and now with experimental MagicWan2.1)~ Heya! I've updated the Wan version with my much better training settings that I've developed! It should be /much/ better now and I improved the captions to support "wide shot/medium shot/medium close up/close up" like my other models do. From my tests the overall quality, motion and everything is improved significantly. If you have any issues with blurred faces or face out of frame please add "blurred face" or "face out of frame" to your negative! Enjoy! Training was exactly like my WanNipplePlay model: https://civitai.com/models/1590451/both-hands-sensual-nipple-play-selfother?modelVersionId=1799759 Experimental MagicWan: Latest version "MagicWan" for Wan2.1 is up! It's experimental and my first attempt at training a LoRA for Wan. I used the same settings and dataset I'd used for 1.5 Hunyuan but lower res. By 3600 steps it was COOKED, but epoch 56 around 2000 steps seems usable though it can definitely be improved! Feedback is welcome and I will definitely be attempting to improve it. Oh and please let me know in the comments if there is any interest in a version for the 1.3B model, I don't use it personally but I'd be happy to train a version for it if it's desired! MagicWand 1.5: New version is up! Featuring much better quality overall, it was trained on a 25% larger dataset at 8e-5 for 3600 steps. It can prompt for corded/cordless (specify either before the color but note that non-white corded models are very limited in dataset and in porn in general so ymmv there) and a bit better for the motion of the vibrator(can append either "vigorously rubbing it up and down" or "grinding herself against it/she is grinding herself against it" to the trigger, results may be seed dependent for grinding especially). For instance: "a nude young woman is reclining on a bed while her girlfriend uses a cordless white MgcWndVb to stimulate her vagina, vigorously rubbing it up and down. She has messy blonde hair and large breasts. Her girlfriend has red hair and is wearing black lingerie. Their faces are close together and they are looking directly into each other's eyes as they share this intense moment of intimacy" It should also handle prompts for couples better. I noticed that "her vagina is wet" doesn't work as well as it did in 1.0 though and instead... kinda makes her squirt a bit sometimes? More testing is needed there. MagicWand 1.0: Good vibrations are coming! Hey all, this is my second LoRA for HunyuanVideo and it turned out /really/ well in my opinion. It produces videos of women either using a magic wand style vibrator on themselves or having one used on them by another man/woman. It was trained at Rank 16 with blurred faces(captioned "blurred out face") so it should be highly compatible with your character LoRA. It learned the motion well enough you can often see the woman's vagina undulating with the vibrations of the wand! Captions/Prompting: "a nude woman is reclining on a kitchen chair with her legs spread while a man standing behind her uses a purple MgcWndVb to stimulate her vagina, rubbing it up and down. She has dark brown hair, small breasts, and her vagina is wet. He has gray hair and is wearing a dark gray shirt. Behind them is a large bed with a black and white painting hanging above it and on the left appears to be a sliding glass door and another painting" "a nude woman with dark hair is using a black MgcWndVb to stimulate her vagina. She arches her back and bends forward as she begins having an orgasm. A tattoo is visible on her hip and her bellybutton is pierced." The trigger should be "using a {black/white/purple/pink} MgcWndVb to stimulate her vagina." Several of the data points also showed the woman wet with arousal and were tagged "Her vagina is wet" so that's promptable too, as is the motion of the wand to a degree. It should be capable of creating solo female, female/female, and male/female scenes. The dataset was quite varied and included various positions, ages of women, ethnicities, aspect ratios etc so try it out I hoped to make it versatile! Training notes: I've learned that high resolutions are not needed for training Hunyuan(Sauce: https://civitai.com/articles/11942/training-a-lora-the-right-way ), at least for motion LoRAs. This LoRA was trained on 15 videos that were preprocessed to six seconds long at 24 fps. A simple python script was used to employ Yolov8X-face detection and then apply a heavy Gaussian blur to faces in order to maintain face agnostic behavior(captioned accordingly). These were then VAE encoded to a combination of 424x240@129f and 640x360@41f and trained in about 12 hours on my 4070TI Super with Musubi Tuner. LR was 1.2e-4 with a LoraPlus multiplier of 4 for 2400 steps using CAME optimizer and constant with warmup scheduler and 100 warmup steps. Final Notes: Ever used one of these things yourself or had one used on you? If not, you should try! It will break your mind in the very best way 😉 Oh also, I've got a few utility scripts I use when creating video datasets for like chunking up videos, normalizing frame rate, blurring faces, etc. Nothing special, don't expect too much; they are just simple CLI affairs but if you are like me and use a largely CLI workflow, they could be helpful: https://github.com/Sarania/videoprocessingscripts They've been written and tested on Linux but should work on Windows too. Depends on Python3, ffmpeg, opencv, and ultralytics. Feel free to use them or not I just thought they might be useful especially the yolov blurring one!
+
+---
+
+## Civitai Links
+
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1314924?modelVersionId=1804710)**
+*   [View Full Model Page →](https://civitai.com/models/1314924)
+*   [View Creator Profile →](https://civitai.com/user/blyss)
+
+---
+
+## File Information
+
+*   **Filename (Saved Locally)**: `WanMagicWand.safetensors`
+*   **Filename (Civitai)**: `WanMagicWand.safetensors`
+*   **Size**: 146.35 MB
+*   **Hash (AutoV2)**: `6EBCDD8F2A`
+
+---
+*Downloaded locally using CivitaiLocalDownloader/1.4-SpecificVersions-NoCreatorFolder.*

M/Magic_Wand_Vibrator_(self-other)_(Hunyuan-Wan)/WanMagicWand.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ebcdd8f2a20bc256d306981a48632a2352b0c020872cedd4544b55a18c2370a
+size 153454712

M/Mayuzumi_Kai-黛灰___hunyuan_video/njsj_mayuzumi_kai.md

@@ -0,0 +1,41 @@
+# Mayuzumi Kai/黛灰 | hunyuan video (Version: v1.0)
+
+**Creator**: [kihh](https://civitai.com/user/kihh)
+**Type**: LORA
+**Base Model**: Hunyuan Video
+**Version Uploaded**: 2025-05-10
+**Trigger Words**: `Mayuzumi Kai, anime-style boy. The image features an anime-style character with dark hair that has a mix of black and that has a slight blue tint at the tips. The hair is styled in a casual manner, with some strands falling over the forehead and others framing the sides. The character's eyes are green, and they have a calm and relaxed expression.The character is wearing a black shirt with white trim on the sleeves and collar. Over the shirt, they have on a white jacket with black accents and a hood. The jacket is open, revealing the shirt underneath.The jacket has a high collar and appears to be made of a lightweight material.`
+
+**Civitai Model ID**: 1565021
+**Civitai Version ID**: 1770972
+
+**Stats (at time of fetch for this version)**:
+*   Downloads: 26
+*   Rating: 0 (0 ratings)
+*   Favorites: N/A
+
+---
+
+## 📄 Description (Parent Model)
+
+This lora depicts the character Mayuzumi Kai(黛灰) from Nijisanji Trigger Word: Mayuzumi Kai, anime-style boy. The image features an anime-style character with dark hair that has a mix of black and that has a slight blue tint at the tips. The hair is styled in a casual manner, with some strands falling over the forehead and others framing the sides. The character's eyes are green, and they have a calm and relaxed expression.The character is wearing a black shirt with white trim on the sleeves and collar. Over the shirt, they have on a white jacket with black accents and a hood. The jacket is open, revealing the shirt underneath.The jacket has a high collar and appears to be made of a lightweight material. Trained: musubi-tuner, 30 images Caption: adjusted caption from Qwen2.5-VL-3B (includes described background) lr:(2e-4,flow_shift7.0) epoch:120 train_step:3600 lora_strength:0.8 sample prompt: Mayuzumi Kai, anime-style boy. The image features an anime-style character with dark hair that has a mix of black and that has a slight blue tint at the tips. The hair is styled in a casual manner, with some strands falling over the forehead and others framing the sides. The character's eyes are green, and they have a calm and relaxed expression.The character is wearing a black shirt with white trim on the sleeves and collar. Over the shirt, they have on a white jacket with black accents and a hood. The jacket is open, revealing the shirt underneath.The jacket has a high collar and appears to be made of a lightweight material. (she is dancing:2.5), (chibi Nendoroid:3.5) in bedroom. アクションは強調promptによって2.0～4.0に調整する必要があります。またはモーションloraを併用ください。 Action prompt should be adjusted to 2.0 to 4.0 depending on emphasis prompt. Or motion lora use together.
+
+---
+
+## Civitai Links
+
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1565021?modelVersionId=1770972)**
+*   [View Full Model Page →](https://civitai.com/models/1565021)
+*   [View Creator Profile →](https://civitai.com/user/kihh)
+
+---
+
+## File Information
+
+*   **Filename (Saved Locally)**: `njsj_mayuzumi_kai.safetensors`
+*   **Filename (Civitai)**: `njsj_mayuzumi_kai.safetensors`
+*   **Size**: 225.06 MB
+*   **Hash (AutoV2)**: `5861CAED0A`
+
+---
+*Downloaded locally using CivitaiLocalDownloader/1.4-SpecificVersions-NoCreatorFolder.*

M/Mayuzumi_Kai-黛灰___hunyuan_video/njsj_mayuzumi_kai.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5861caed0a48d454861fa65dd18f191ed42c968e8aff5d7548f88b30d682bc33
+size 235994128

M/Melody_(Hunyuan)/MelodyHunyuan.md

@@ -0,0 +1,41 @@
+# Melody (Hunyuan) (Version: Melody (Hunyuan))
+
+**Creator**: [Stinslow](https://civitai.com/user/Stinslow)
+**Type**: LORA
+**Base Model**: Hunyuan Video
+**Version Uploaded**: 2025-05-07
+**Trigger Words**: `N/A`
+
+**Civitai Model ID**: 1554379
+**Civitai Version ID**: 1758871
+
+**Stats (at time of fetch for this version)**:
+*   Downloads: 116
+*   Rating: 0 (0 ratings)
+*   Favorites: N/A
+
+---
+
+## 📄 Description (Parent Model)
+
+This is a fictional character I created by combining a a few other LoRA's.  Feel free to use it
+
+---
+
+## Civitai Links
+
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1554379?modelVersionId=1758871)**
+*   [View Full Model Page →](https://civitai.com/models/1554379)
+*   [View Creator Profile →](https://civitai.com/user/Stinslow)
+
+---
+
+## File Information
+
+*   **Filename (Saved Locally)**: `MelodyHunyuan.safetensors`
+*   **Filename (Civitai)**: `MelodyHunyuan.safetensors`
+*   **Size**: 225.09 MB
+*   **Hash (AutoV2)**: `28B6AC18C5`
+
+---
+*Downloaded locally using CivitaiLocalDownloader/1.4-SpecificVersions-NoCreatorFolder.*

M/Melody_(Hunyuan)/MelodyHunyuan.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b6ac18c5bc7715c5676246331d6d5ff2286aa2a87f6239a3b18bb4af75923c
+size 236019024

M/Minato_Aqua-湊あくあ___hunyuan_video/vtuber_minato_aqua.md

@@ -0,0 +1,41 @@
+# Minato Aqua/湊あくあ | hunyuan video (Version: v1.0)
+
+**Creator**: [kihh](https://civitai.com/user/kihh)
+**Type**: LORA
+**Base Model**: Hunyuan Video
+**Version Uploaded**: 2025-05-10
+**Trigger Words**: `Minato Aqua, anime-style girl. The image features an anime-style character with pink hair styled in twin tails. The hair is adorned with white ribbons and a small bow at the front. The character has purple eyes and is wearing a sailor-style dress with a blue and white color scheme. The dress includes a white collar, a blue bodice with a bow, and a blue skirt with white trim and bows.The dress has multiple bows and a sailor hat with an anchor emblem on top.`
+
+**Civitai Model ID**: 1564772
+**Civitai Version ID**: 1770687
+
+**Stats (at time of fetch for this version)**:
+*   Downloads: 35
+*   Rating: 0 (0 ratings)
+*   Favorites: N/A
+
+---
+
+## 📄 Description (Parent Model)
+
+This lora depicts the character Minato Aqua(湊あくあ) Trigger Word: Minato Aqua, anime-style girl. The image features an anime-style character with pink hair styled in twin tails. The hair is adorned with white ribbons and a small bow at the front. The character has purple eyes and is wearing a sailor-style dress with a blue and white color scheme. The dress includes a white collar, a blue bodice with a bow, and a blue skirt with white trim and bows.The dress has multiple bows and a sailor hat with an anchor emblem on top. Trained: musubi-tuner, 30 images Caption: adjusted caption from Qwen2.5-VL-3B (includes described background) lr:(2e-4,flow_shift7.0) epoch:120 train_step:3600 lora_strength:0.8 sample prompt: Minato Aqua, anime-style girl. The image features an anime-style character with pink hair styled in twin tails. The hair is adorned with white ribbons and a small bow at the front. The character has purple eyes and is wearing a sailor-style dress with a blue and white color scheme. The dress includes a white collar, a blue bodice with a bow, and a blue skirt with white trim and bows.The dress has multiple bows and a sailor hat with an anchor emblem on top. (she is dancing:2.5), (chibi Nendoroid:3.5) in bedroom. アクションは強調promptによって2.0～4.0に調整する必要があります。またはモーションloraを併用ください。 Action prompt should be adjusted to 2.0 to 4.0 depending on emphasis prompt. Or motion lora use together.
+
+---
+
+## Civitai Links
+
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1564772?modelVersionId=1770687)**
+*   [View Full Model Page →](https://civitai.com/models/1564772)
+*   [View Creator Profile →](https://civitai.com/user/kihh)
+
+---
+
+## File Information
+
+*   **Filename (Saved Locally)**: `vtuber_minato_aqua.safetensors`
+*   **Filename (Civitai)**: `vtuber_minato_aqua.safetensors`
+*   **Size**: 225.06 MB
+*   **Hash (AutoV2)**: `1086B86424`
+
+---
+*Downloaded locally using CivitaiLocalDownloader/1.4-SpecificVersions-NoCreatorFolder.*

M/Minato_Aqua-湊あくあ___hunyuan_video/vtuber_minato_aqua.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1086b8642428234cb40ac9df8fa9d42b5fa94deba3ad0f97102d2da647e50341
+size 235994128

M/Muscle_Mommy/muscle_mommy_v2_epoch14.md

@@ -0,0 +1,45 @@
+# Muscle Mommy (Version: Ripped)
+
+**Creator**: [KinkMaster](https://civitai.com/user/KinkMaster)
+**Type**: LORA
+**Base Model**: Hunyuan Video
+**Version Uploaded**: 2025-02-27
+**Trigger Words**: `muscle_mommy`
+
+**Civitai Model ID**: 1300229
+**Civitai Version ID**: 1467660
+
+**Stats (at time of fetch for this version)**:
+*   Downloads: 372
+*   Rating: 0 (0 ratings)
+*   Favorites: N/A
+
+---
+
+## 📄 Description (Parent Model)
+
+This lora is a request made by a user on civitai to help them make realistic hyper-muscular women. Not quite sure how I feel about this one... Hunyuan seems to really fight this lora sometimes and it doesn't play too well with motion loras. I suspect that is because the motion loras inherently have trained bias toward the look of its subjects which can overwhelm this character lora. Still, I wanted to share for anyone interested. I'll be uploading two versions: Smol: Trained on all blocks for roughly 1600 steps. It feels a bit undercooked, but can make some decent looking buff/ripped women. It can also make hyper-muscular women too. Ripped: Trained on double blocks only for closer to 2600 steps. This lora will generate all the hyper-muscular women in the world if you so want it to. It plays a bit better with other loras, but can still be overpowered at times. Neither version is perfect. I rarely used 1.00 weight with either of these. Test and use what works well for you. Trigger word is: muscle_mommy I'd also recommend using terms like: hyper-muscular woman with extremely large muscles, flexing her muscles As this was a request from a user, I won't likely return to this. So unlike these women, you probably won't find me back in this gym any time soon. Use with the Hunyuan Goonmaker workflow to achieve similar results: https://civitai.com/models/1315959?modelVersionId=1485540
+
+## Version Notes (Ripped)
+
+Trained on double blocks only. Data set consists of both nude and clothed hyper-muscular women.
+
+---
+
+## Civitai Links
+
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1300229?modelVersionId=1467660)**
+*   [View Full Model Page →](https://civitai.com/models/1300229)
+*   [View Creator Profile →](https://civitai.com/user/KinkMaster)
+
+---
+
+## File Information
+
+*   **Filename (Saved Locally)**: `muscle_mommy_v2_epoch14.safetensors`
+*   **Filename (Civitai)**: `muscle_mommy_v2_epoch14.safetensors`
+*   **Size**: 172.55 MB
+*   **Hash (AutoV2)**: `DF6A0C7333`
+
+---
+*Downloaded locally using CivitaiLocalDownloader/1.4-SpecificVersions-NoCreatorFolder.*

M/Muscle_Mommy/muscle_mommy_v2_epoch14.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6a0c7333d67158b3047fdc478a59eef3f806d683baecd3054962da9f20cda6
+size 180930896