OrangeCatapult20 commited on
Commit
062e6dc
β€’
1 Parent(s): 7dfd70e

Added new lora

Browse files
README.md CHANGED
@@ -7,30 +7,59 @@ tags:
7
 
8
  # Trained LoRAs
9
 
10
- I will upload all of LoRAs that I trained here on my free time. The model I mostly used with these previews will be AnyV3 or AOM2. I haven't tested it on other models but it may or may not work :/ I also just started learning on doing training this month so the quality may not be good as I'm still a noob with this stuff πŸ˜… (For example, you may still need to specify some character traits on the prompt to be more accurate.)
 
11
 
12
- Some negative embeddings I may use on sample images will be bad_prompt, bad-artist, or bad-image.
 
 
 
 
13
 
14
  # Previews
15
 
16
- - ## Satono Diamond (Uma Musume)
17
- [<img src="https://huggingface.co/OrangeCatapult20/trained-loras/resolve/main/previews/1.png" width="512" height="768">](https://huggingface.co/OrangeCatapult20/trained-loras/resolve/main/previews/1.png)
18
- <details>
19
- <summary>Sample Prompt</summary>
20
- <pre>
 
 
 
 
 
 
 
21
  masterpiece, best quality, 1girl, solo, satono diamond, horse ears
22
  <b>Negative prompt:</b> lowres, ((bad anatomy)), ((bad hands)), text, missing finger, extra digits, fewer digits, blurry, ((mutated hands and fingers)), (poorly drawn face), ((mutation)), ((deformed face)), (ugly), ((bad proportions)), ((extra limbs)), extra face, (double head), (extra head), ((extra feet)), monster, logo, cropped, worst quality, low quality, normal quality, jpeg, humpbacked, long body, long neck, ((jpeg artifacts))
23
  Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 3393568171, Size: 512x768, Model hash: 0fc198c490, Clip skip: 2, ENSD: 31337, AddNet Enabled: True, AddNet Module 1: LoRA, AddNet Model 1: satono_diamond(aff3460f), AddNet Weight 1: 0.54
24
- </pre>
25
- </details>
26
-
27
- - ## Mihono Bourbon (Uma Musume)
28
- [<img src="https://huggingface.co/OrangeCatapult20/trained-loras/resolve/main/previews/2.png" width="512" height="768">](https://huggingface.co/OrangeCatapult20/trained-loras/resolve/main/previews/2.png)
29
- <details>
30
- <summary>Sample Prompt</summary>
31
- <pre>
32
  masterpiece, best quality, ray tracing, bloom, 1girl, solo, mihono bourbon, horse ears, blue eyes, umamusume, bare shoulders, closed mouth, ahoge, pleated skirt, detached sleeves, necktie, miniskirt, thighhighs, leotard, covered navel, highleg leotard, lowleg skirt
33
  <b>Negative prompt:</b> (bad-image-v2:0.8), lowres, mutated hands and fingers, extra legs, extra limbs, fused fingers, simple background, white background, letterboxed, out of frame, border, monster, mutated, bad anatomy, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, (worst quality, low quality:1.3), normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, copyright name, watermark
34
  Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 8, Seed: 3193256216, Size: 512x768, Model hash: 0fc198c490, Clip skip: 2, ENSD: 31337, AddNet Enabled: True, AddNet Module 1: LoRA, AddNet Model 1: mihono_bourbon(e038379e), AddNet Weight 1: 1
35
- </pre>
36
- </details>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
 
8
  # Trained LoRAs
9
 
10
+ - [Overview](#overview)
11
+ - [Previews](#previews)
12
 
13
+ # Overview
14
+
15
+ I will upload all of LoRAs that I trained here on my free time. The model I mostly used with these previews will be [AnyV4.5](https://huggingface.co/andite/anything-v4.0) or [AOM2](https://huggingface.co/WarriorMama777/OrangeMixs). I haven't tested it on other models but it may or may not work :/ I also just started learning on doing training so the quality may not be good as I'm still a noob with this stuff πŸ˜… (For example, you may still need to specify some character traits on the prompt to be more accurate.)
16
+
17
+ Some negative embeddings I may use on sample images will be bad-prompt, bad-artist, or bad-image.
18
 
19
  # Previews
20
 
21
+ - [Uma Musume: Pretty Derby](#uma-musume-pretty-derby)
22
+ 1. [Satono Diamond](#satono-diamond)
23
+ 2. [Mihono Bourbon](#mihono-bourbon)
24
+ - [Style LoRAs](#art-styles)
25
+
26
+ ## Uma Musume: Pretty Derby
27
+
28
+ - ### Satono Diamond
29
+ <img src="https://huggingface.co/OrangeCatapult20/trained-loras/resolve/main/previews/1.png" width="512" height="768">
30
+ <details>
31
+ <summary>Sample Prompt</summary>
32
+ <pre>
33
  masterpiece, best quality, 1girl, solo, satono diamond, horse ears
34
  <b>Negative prompt:</b> lowres, ((bad anatomy)), ((bad hands)), text, missing finger, extra digits, fewer digits, blurry, ((mutated hands and fingers)), (poorly drawn face), ((mutation)), ((deformed face)), (ugly), ((bad proportions)), ((extra limbs)), extra face, (double head), (extra head), ((extra feet)), monster, logo, cropped, worst quality, low quality, normal quality, jpeg, humpbacked, long body, long neck, ((jpeg artifacts))
35
  Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 3393568171, Size: 512x768, Model hash: 0fc198c490, Clip skip: 2, ENSD: 31337, AddNet Enabled: True, AddNet Module 1: LoRA, AddNet Model 1: satono_diamond(aff3460f), AddNet Weight 1: 0.54
36
+ </pre>
37
+ </details>
38
+
39
+ - ### Mihono Bourbon
40
+ <img src="https://huggingface.co/OrangeCatapult20/trained-loras/resolve/main/previews/2.png" width="512" height="768">
41
+ <details>
42
+ <summary>Sample Prompt</summary>
43
+ <pre>
44
  masterpiece, best quality, ray tracing, bloom, 1girl, solo, mihono bourbon, horse ears, blue eyes, umamusume, bare shoulders, closed mouth, ahoge, pleated skirt, detached sleeves, necktie, miniskirt, thighhighs, leotard, covered navel, highleg leotard, lowleg skirt
45
  <b>Negative prompt:</b> (bad-image-v2:0.8), lowres, mutated hands and fingers, extra legs, extra limbs, fused fingers, simple background, white background, letterboxed, out of frame, border, monster, mutated, bad anatomy, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, (worst quality, low quality:1.3), normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, copyright name, watermark
46
  Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 8, Seed: 3193256216, Size: 512x768, Model hash: 0fc198c490, Clip skip: 2, ENSD: 31337, AddNet Enabled: True, AddNet Module 1: LoRA, AddNet Model 1: mihono_bourbon(e038379e), AddNet Weight 1: 1
47
+ </pre>
48
+ </details>
49
+
50
+ # Art Styles
51
+
52
+ Test
53
+
54
+ - ### Lillly
55
+
56
+ [Artist Twitter](https://twitter.com/lillly____?s=20)
57
+
58
+ <img src="https://huggingface.co/OrangeCatapult20/trained-loras/resolve/main/previews/3.png" width="512" height="768">
59
+ <details>
60
+ <summary>Sample Prompt</summary>
61
+ <pre>
62
+ masterpiece, best quality, ultra-detailed, bloom, delicate and beautiful, (from above:1.2), 1girl, solo, beautiful eyes, fox ears, fox tail, fox girl, large breasts, red hair, white dress, see-through, breasts out, open clothes, bottomless, water on breasts, forest background &lt;lora:lillly-style:0.65&gt;
63
+ <b>Negative prompt:</b> (painting by bad-artist-anime:0.9), (painting by bad-artist:0.9), watermark, text, error, blurry, jpeg artifacts, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, artist name, (worst quality, low quality:1.4), bad anatomy Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 6.5, Seed: 4158263580, Size: 512x768, Model hash: f773383dbc, Clip skip: 2, ENSD: 31337
64
+ </pre>
65
+ </details>
loras/{mihono_bourbon.safetensors β†’ characters/mihono_bourbon.safetensors} RENAMED
File without changes
loras/{satono_diamond.safetensors β†’ characters/satono_diamond.safetensors} RENAMED
File without changes
loras/styles/lillly-style.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a8246c09705dc2dc79fe2f6ff1e181ea731daf2dab84cf27c20a56b7a3f6cfe
3
+ size 302069804
previews/3.png ADDED