fzbuzz commited on
Commit
ad7a82d
1 Parent(s): 9ee7d45

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -11
README.md CHANGED
@@ -7,6 +7,15 @@ license: openrail
7
  The embedding were trained using A1111 TI for the 768px Stable Diffusion v2.0 model.
8
  The embedding should work on any model that uses SD v2.0 as a base.
9
 
 
 
 
 
 
 
 
 
 
10
  <div align="center">
11
  <img src="https://huggingface.co/fzbuzz/TungstenDispo-embedding-sd-v2-1/resolve/main/00000.png">
12
  </div>
@@ -23,18 +32,9 @@ The embedding should work on any model that uses SD v2.0 as a base.
23
  <img src="https://huggingface.co/fzbuzz/TungstenDispo-embedding-sd-v2-1/resolve/main/00003.png">
24
  </div>
25
 
26
- **Usage for A1111 WebUI**
27
- Download the TungstenDispo.pt file and put in embeddings/. Prepend "TungstenDispo" at start of prompt.
28
-
29
- **TungstenDispo (v1)**
30
-
31
- The TungstenDispo embedding were trained for 1000 epochs with a gradient batch size of 50.
32
- A total of ~100 training images of tungsten photographs taken with CineStill 800T were used. The split was around 50/50 people landscapes.
33
- The effect isn't quite the tungsten photo effect I was going for, but creates very nice, artistic portraits of people.
34
- Landscapes haven't been experimented with much. For some of the people, I used SoCalGuitarist's [Negative FaceLift](https://civitai.com/models/2385/socalguitarists-magic-facelift-negative-embedding-for-model-2x-fix-yo-ugly-faces) as a negative embedding.
35
- I used it on 0.3 strength, and it seems like it makes the eyes slightly less wonky. Unclear extent of effect.
36
-
37
  **Workflow for Above Pictures**
 
38
  Sampler: Euler-A, 20 Steps, CFG: 7.0. Slightly cherry-picked for best pictures.
39
  900x768 -> 4x LDSR upscaled
40
 
@@ -43,7 +43,13 @@ Negative Prompt for all images (Not entirely sure if all of them matter, but doe
43
 
44
  TungstenDispo, photoshoot of a old man, highly detailed
45
 
 
 
 
 
 
46
  **More People Samples w/out exact workflow**
 
47
  Pretty much the same, only changed up subject a little + weights.
48
 
49
  <div align="center">
 
7
  The embedding were trained using A1111 TI for the 768px Stable Diffusion v2.0 model.
8
  The embedding should work on any model that uses SD v2.0 as a base.
9
 
10
+ **TungstenDispo (v1)**
11
+
12
+ The TungstenDispo embedding were trained for 1000 epochs with a gradient batch size of 50.
13
+ A total of ~100 training images of tungsten photographs taken with CineStill 800T were used. The split was around 50/50 people landscapes.
14
+ The effect isn't quite the tungsten photo effect I was going for, but creates very nice, artistic portraits of people.
15
+ Landscapes haven't been experimented with much. For some of the people, I used SoCalGuitarist's [Negative FaceLift](https://civitai.com/models/2385/socalguitarists-magic-facelift-negative-embedding-for-model-2x-fix-yo-ugly-faces) as a negative embedding.
16
+ I used it on 0.3 strength, and it seems like it makes the eyes slightly less wonky. Unclear extent of effect.
17
+
18
+
19
  <div align="center">
20
  <img src="https://huggingface.co/fzbuzz/TungstenDispo-embedding-sd-v2-1/resolve/main/00000.png">
21
  </div>
 
32
  <img src="https://huggingface.co/fzbuzz/TungstenDispo-embedding-sd-v2-1/resolve/main/00003.png">
33
  </div>
34
 
35
+ ---
 
 
 
 
 
 
 
 
 
 
36
  **Workflow for Above Pictures**
37
+
38
  Sampler: Euler-A, 20 Steps, CFG: 7.0. Slightly cherry-picked for best pictures.
39
  900x768 -> 4x LDSR upscaled
40
 
 
43
 
44
  TungstenDispo, photoshoot of a old man, highly detailed
45
 
46
+ **Usage for A1111 WebUI**
47
+
48
+ Download the TungstenDispo.pt file and put in embeddings/. Prepend "TungstenDispo" at start of prompt.
49
+
50
+
51
  **More People Samples w/out exact workflow**
52
+
53
  Pretty much the same, only changed up subject a little + weights.
54
 
55
  <div align="center">