Upload T2V_HIGH/README.md with huggingface_hub
Browse files- T2V_HIGH/README.md +62 -0
T2V_HIGH/README.md
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
tags:
|
| 5 |
+
- art
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
# Back Bending. Contortion. Flexshow
|
| 9 |
+
|
| 10 |
+
**Creator**: [wuleshome](https://civitai.com/user/wuleshome)
|
| 11 |
+
**Type**: LORA
|
| 12 |
+
**Base Model**: Wan Video 2.2 T2V-A14B
|
| 13 |
+
**Version**: T2V_HIGH
|
| 14 |
+
**Trigger Words**: `N/A`
|
| 15 |
+
|
| 16 |
+
**Civitai Model ID**: 1891926
|
| 17 |
+
**Civitai Version ID**: 2141473
|
| 18 |
+
|
| 19 |
+
**Stats (at time of fetch for this version)**:
|
| 20 |
+
* Downloads: 337
|
| 21 |
+
* Rating: 0 (0 ratings)
|
| 22 |
+
* Favorites: N/A
|
| 23 |
+
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
## 📄 Description (Parent Model)
|
| 27 |
+
|
| 28 |
+
This is an experimental piece. I just wanted to test whether some poses that defy normal human body structure could be effectively trained into a Lora, and the results have been very satisfying! This motivates me to expand the dataset
|
| 29 |
+
I only used six 33-frame videos to train it, and three of those videos were generated by me using wan2.1 vace. This was challenging because DWpose couldn't recognize these unusual movements!
|
| 30 |
+
I only tried testing it with some simple prompts; you can try using complex prompts and hopefully it will perform well too.
|
| 31 |
+
Tested at
|
| 32 |
+
480x848
|
| 33 |
+
and
|
| 34 |
+
720x1280
|
| 35 |
+
resolutions, not sure how it performs at other resolutions.
|
| 36 |
+
The girl is wearing a blue bikini and black high heels,
|
| 37 |
+
showcasing the "sanzhe" pose on a dimly lit stage,
|
| 38 |
+
holding the tips of her shoes with both hands, her face showing pain
|
| 39 |
+
I've only tested it using
|
| 40 |
+
wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors with 4-step sampling
|
| 41 |
+
I don't know how this Lora performs without acceleration.
|
| 42 |
+
|
| 43 |
+
## Version Notes (T2V_HIGH)
|
| 44 |
+
|
| 45 |
+
Wan2.2 T2V HIGH
|
| 46 |
+
|
| 47 |
+
---
|
| 48 |
+
|
| 49 |
+
## Civitai Links
|
| 50 |
+
|
| 51 |
+
* **[🔗 View This Version on Civitai →](https://civitai.com/models/1891926?modelVersionId=2141473)**
|
| 52 |
+
* [View Full Model Page →](https://civitai.com/models/1891926)
|
| 53 |
+
* [View Creator Profile →](https://civitai.com/user/wuleshome)
|
| 54 |
+
|
| 55 |
+
---
|
| 56 |
+
|
| 57 |
+
## File Information
|
| 58 |
+
|
| 59 |
+
* **Filename**: `adapter_model_H_335.safetensors`
|
| 60 |
+
* **Size**: 292.59 MB
|
| 61 |
+
* **Hash (AutoV2)**: `2EDBEBE04D`
|
| 62 |
+
* **Hash (SHA256)**: `2EDBEBE04DF4FC392157F1416C546D223FEA8B1C769383120923554263AA8039`
|