Upload v2.0/README.md with huggingface_hub
Browse files- v2.0/README.md +63 -0
v2.0/README.md
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
tags:
|
| 5 |
+
- art
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
# Reality Simulator
|
| 9 |
+
|
| 10 |
+
**Creator**: [vjleoliu](https://civitai.com/user/vjleoliu)
|
| 11 |
+
**Type**: LORA
|
| 12 |
+
**Base Model**: Qwen
|
| 13 |
+
**Version**: v2.0
|
| 14 |
+
**Trigger Words**: `N/A`
|
| 15 |
+
|
| 16 |
+
**Civitai Model ID**: 1886273
|
| 17 |
+
**Civitai Version ID**: 2171888
|
| 18 |
+
|
| 19 |
+
**Stats (at time of fetch for this version)**:
|
| 20 |
+
* Downloads: 1205
|
| 21 |
+
* Rating: 0 (0 ratings)
|
| 22 |
+
* Favorites: N/A
|
| 23 |
+
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
## 📄 Description (Parent Model)
|
| 27 |
+
|
| 28 |
+
This model is specifically designed to simulate the real world. Photos taken by smartphones are carefully selected as the training set, enabling the model to have a better real - life texture. The LoRA weight of Qwen-image can be increased to 2, but it is recommended not to exceed 1.8. The initialization can start from 0.6, and generally, a value between 0.9 and 1.2 works well. The following is a set of image comparisons.
|
| 29 |
+
Parameter Recommendations
|
| 30 |
+
Recommended Weight
|
| 31 |
+
: 0.6 - 1.5 (default 0.9)
|
| 32 |
+
Recommended Size
|
| 33 |
+
: 768/1024/1536 (default 1024)
|
| 34 |
+
Sampling Algorithm
|
| 35 |
+
: 3.0 - 3.5 (default 3.5)
|
| 36 |
+
Step
|
| 37 |
+
: 20 - 40 (With the acceleration model, it can be reduced to 4 - 8 steps)
|
| 38 |
+
Sampler
|
| 39 |
+
: euler/heun
|
| 40 |
+
Cover Prompt Examples:
|
| 41 |
+
从侧面拍摄,一位亚洲女性坐在电影院的红色座椅上,她转头微笑着看向镜头,穿着黑色皮夹克,长发披肩,略带卷曲。她右手拿着一个大号的纸杯,杯身印有红色和白色图案,杯中插着一根吸管,她正用吸管喝着饮料。左手拿着一块食物,看起来像是一个包裹在纸巾里的三明治或汉堡,正准备吃。
|
| 42 |
+
背景是昏暗的电影院内部,巨大的电影幕布上呈现出标题“Reality Simulator”,上方有微弱的灯光,天花板上有一些光斑,可能是放映时的反光或灯光效果。周围的座椅都是深红色的,呈弧形排列,营造出一种安静、私密的观影氛围。
|
| 43 |
+
|
| 44 |
+
## Version Notes (v2.0)
|
| 45 |
+
|
| 46 |
+
From the newly organized dataset, we hope to replicate the photography texture of old-fashioned smartphones, adding authenticity and a sense of life to the images.
|
| 47 |
+
|
| 48 |
+
---
|
| 49 |
+
|
| 50 |
+
## Civitai Links
|
| 51 |
+
|
| 52 |
+
* **[🔗 View This Version on Civitai →](https://civitai.com/models/1886273?modelVersionId=2171888)**
|
| 53 |
+
* [View Full Model Page →](https://civitai.com/models/1886273)
|
| 54 |
+
* [View Creator Profile →](https://civitai.com/user/vjleoliu)
|
| 55 |
+
|
| 56 |
+
---
|
| 57 |
+
|
| 58 |
+
## File Information
|
| 59 |
+
|
| 60 |
+
* **Filename**: `iphone.safetensors`
|
| 61 |
+
* **Size**: 562.72 MB
|
| 62 |
+
* **Hash (AutoV2)**: `06FEB3E6AB`
|
| 63 |
+
* **Hash (SHA256)**: `06FEB3E6AB4B996BD4E00978DA9DA4CB138C5C25BB2C947DF555C0D18D099598`
|