Update README.md
Browse files
README.md
CHANGED
@@ -12,8 +12,7 @@ tags:
|
|
12 |
- stable-diffusion-xl
|
13 |
- merge
|
14 |
base_model:
|
15 |
-
-
|
16 |
-
- Laxhar/noobai-XL-Vpred-0.6
|
17 |
---
|
18 |
|
19 |
<style>
|
@@ -38,8 +37,8 @@ base_model:
|
|
38 |
|
39 |
## NOTICE
|
40 |
- This is a v-prediction model.
|
41 |
-
-
|
42 |
-
-
|
43 |
|
44 |
<div class="gallery">
|
45 |
<img src="./sample01.webp" alt="sample_v11_1">
|
@@ -53,31 +52,30 @@ base_model:
|
|
53 |
- **License**: [Fair AI Public License 1.0-SD](https://freedevproject.org/faipl-1.0-sd/)
|
54 |
|
55 |
## Merge Recipe
|
56 |
-
-
|
57 |
-
- (https://civitai.com/models/846917/raehoshi-illust-xl)
|
58 |
-
- RouWei 0.6.1 vpred (B)
|
59 |
- (https://civitai.com/models/950531/rouwei)
|
60 |
-
-
|
61 |
-
-
|
62 |
-
-
|
63 |
-
- (https://
|
64 |
-
- SPO-SDXL_4k-p_10ep_LoRA_webui (
|
65 |
- (https://civitai.com/models/510261/spo-sdxl4k-p10eplorawebui)
|
|
|
|
|
66 |
```
|
67 |
-
A + (
|
68 |
-
|
69 |
-
H + F * weight 1.0 = This Model v1.1
|
70 |
```
|
71 |
|
72 |
## Recommended settings
|
73 |
|
74 |
- **Positive prompts:**
|
75 |
```
|
76 |
-
masterpiece, best quality
|
77 |
```
|
78 |
- **Negative prompts:**
|
79 |
```
|
80 |
-
|
81 |
```
|
82 |
- **CFG:** 3-5
|
83 |
- **Sampling steps:** 28
|
@@ -92,6 +90,7 @@ lowres, bad quality, worst quality, very displeasing, bad anatomy, sketch, jpeg
|
|
92 |
- **Hires step:** 10-15
|
93 |
- **Denoising:** 0.3-0.4
|
94 |
|
95 |
-
## License
|
96 |
|
97 |
-
|
|
|
|
|
|
12 |
- stable-diffusion-xl
|
13 |
- merge
|
14 |
base_model:
|
15 |
+
- Minthy/RouWei-0.7
|
|
|
16 |
---
|
17 |
|
18 |
<style>
|
|
|
37 |
|
38 |
## NOTICE
|
39 |
- This is a v-prediction model.
|
40 |
+
- No longer includes noob AI.
|
41 |
+
- 99% of this checkpoint is made with RouWei.
|
42 |
|
43 |
<div class="gallery">
|
44 |
<img src="./sample01.webp" alt="sample_v11_1">
|
|
|
52 |
- **License**: [Fair AI Public License 1.0-SD](https://freedevproject.org/faipl-1.0-sd/)
|
53 |
|
54 |
## Merge Recipe
|
55 |
+
- RouWei 0.7 vpred (A)
|
|
|
|
|
56 |
- (https://civitai.com/models/950531/rouwei)
|
57 |
+
- CyberRealistic XL (B)
|
58 |
+
- (https://civitai.com/models/312530/cyberrealistic-xl)
|
59 |
+
- stable-diffusion-xl-base-1.0 (C)
|
60 |
+
- (https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
|
61 |
+
- SPO-SDXL_4k-p_10ep_LoRA_webui (D)
|
62 |
- (https://civitai.com/models/510261/spo-sdxl4k-p10eplorawebui)
|
63 |
+
- My LoRA (E)
|
64 |
+
- Trained by 300 images AI-generated
|
65 |
```
|
66 |
+
A + (B - C) * 0.5 = F
|
67 |
+
F + D + E * 0.5 = This Model v2.0
|
|
|
68 |
```
|
69 |
|
70 |
## Recommended settings
|
71 |
|
72 |
- **Positive prompts:**
|
73 |
```
|
74 |
+
masterpiece, best quality
|
75 |
```
|
76 |
- **Negative prompts:**
|
77 |
```
|
78 |
+
worst quality, low quality, watermark
|
79 |
```
|
80 |
- **CFG:** 3-5
|
81 |
- **Sampling steps:** 28
|
|
|
90 |
- **Hires step:** 10-15
|
91 |
- **Denoising:** 0.3-0.4
|
92 |
|
|
|
93 |
|
94 |
+
# Thanks
|
95 |
+
- First of all, to Minthy for RouWei. That has the best prompt following I know of!
|
96 |
+
- And, of course, thanks for the Animagine. Animagine was the first signpost that led me to use SDXL, and it continues to do so!
|