6DammK9 commited on
Commit
28c0a22
1 Parent(s): e363aec

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +27 -106
README.md CHANGED
@@ -8,7 +8,7 @@ tags:
8
  - text-to-image
9
  - safetensors
10
  inference: true
11
- thumbnail: https://huggingface.co/6DammK9/AstolfoMix-XL/resolve/main/240234-2213673007-2016-1152-4.5-192-20240210015331.jpg
12
  widget:
13
  - text: >-
14
  aesthetic, quality, 1girl, boy, astolfo
@@ -23,130 +23,51 @@ library_name: diffusers
23
  - Unsolved merge, even with experience on [SD1](https://huggingface.co/6DammK9/AstolfoMix) and [SD2](https://huggingface.co/6DammK9/AstolfoMix-SD2).
24
  - See [full article in Github](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/README_XL.MD)
25
 
26
- ## Baseline ##
27
 
28
- - **Uniform merge** of 32 UNETS + (19+26) CLIPS (from 21 models). Discovered model count: 42.
29
 
30
- - Current version: `x17-AstolfoMix-x13te0x14te1.safetensors`
31
- - Recommended version: "x17" for full experience, or "x11c" for human focused.
32
- - Recommended CFG: 4.5
33
  - *Prompt is minimal.*
34
 
35
- ![240234-2213673007-2016-1152-4.5-192-20240210015331.jpg](https://huggingface.co/6DammK9/AstolfoMix-XL/resolve/main/240234-2213673007-2016-1152-4.5-192-20240210015331.jpg)
36
 
37
  ```
38
  parameters
39
 
40
- (solo:0), (boy:0), (qipao:0.98), [astolfo_\(fate\)], [[lunar new year]], [[[[kowloon]]]]
41
- Steps: 192, Sampler: Euler, CFG scale: 4.5, Seed: 2213673007, Size: 1344x768, Model hash: 82f53a8fe1, Model: x17-AstolfoMix-x13te0x14te1, VAE hash: 26cc240b77, VAE: sd_xl_base_1.0.vae.safetensors, Denoising strength: 0.7, Clip skip: 2, FreeU Stages: "[{\"backbone_factor\": 1.1, \"skip_factor\": 0.6}, {\"backbone_factor\": 1.2, \"skip_factor\": 0.4}]", FreeU Schedule: "0.0, 1.0, 0.0", FreeU Version: 2, Hires upscale: 1.5, Hires upscaler: Latent, Dynamic thresholding enabled: True, Mimic scale: 1, Separate Feature Channels: False, Scaling Startpoint: MEAN, Variability Measure: AD, Interpolate Phi: 0.3, Threshold percentile: 100, Version: v1.7.0
42
- ```
43
-
44
- ## Discovered models ##
45
-
46
-
47
- - Here is a full list of discovered models:
48
-
49
- <details>
50
- <summary>Table with 40+ rows. Click to open.</summary>
51
-
52
- *mega table coming soon*
53
-
54
- ```log
55
- _x01-deepDarkHentaiMixNSFW_v12.safetensors
56
- _x02-animeAntifreezingSolutionXL_v10.safetensors
57
- _x03-hsxl_base_1.0.f16.safetensors
58
- _x04-OpenDalleV1.1.safetensors
59
- _x05-copaxTimelessxlSDXL1_v8.safetensors
60
- _x06-juggernautXL_v8Rundiffusion.safetensors
61
- _x07-kohakuXLBeta_beta7.safetensors
62
- _x08-animagineXLV3_v30.safetensors
63
- _x09-animeboysxl_v10.safetensors
64
- _x10-dreamshaperXL_alpha2Xl10.safetensors
65
- _x11-SDXLRonghua_v40.safetensors
66
- _x12-bluePencilXL_v310.safetensors
67
- _x13-leosamsHelloworldSDXL_helloworldSDXL32DPO.safetensors
68
- _x14-ponyDiffusionV6XL_v6.safetensors
69
- _x15-animagineXL_v20.safetensors
70
- _x16-wdxl-aesthetic-0.9.safetensors
71
- _x17-leosamsHelloworldSDXLModel_helloworldSDXL10.safetensors
72
- _x18-nekoray-xl-1.5m-fp16mixed_e02.safetensors
73
- _x19-nekoray-xl-1.5m-pdg32_e02.safetensors
74
- _x20-explicitFreedomNSFW_beta.safetensors
75
- _x21-nd-run8-weighted-3.safetensors
76
- _x22-kohakuXL_alpha7.safetensors
77
- _x23-nekorayxl_v06W3.safetensors
78
- _x24-SwimInLatent-alpha.fp16.safetensors
79
- _x25-sd_xl_base_1.0.safetensors
80
- _x26-enjoyXLAdvancedEdition_v7AdvancedVersion.safetensors
81
- _x27-explicitFreedomNSFW_alpha.safetensors
82
- _x28-heartOfAppleXL_v10.safetensors
83
- _x29-kohakuXLGamma_rev1.safetensors
84
- _x30-aamXLAnimeMix_v10.safetensors
85
- _x31-counterfeitxl_v25.safetensors
86
- _x32-enjoyPandoraXL_v10.safetensors
87
- _x33-4Guofeng4XL_v12.safetensors
88
- _x34-animeIllustDiffusion_v061.safetensors
89
- _x35-brightprotonukeBPNNo_bpn13.safetensors
90
- _x36-devlishphotorealism_sdxl15.safetensors
91
- _x37-himawarimix_xlV4.safetensors
92
- _x38-aio_v10.safetensors
93
- _x39-sakumix_v10.safetensors
94
- _x40-218xl_.safetensors
95
- _x41-riotDiffusionXLLeagueOfLegendsSplash_v20.safetensors
96
- _x42-himawarimix_xlV5.safetensors
97
- _x43-SDXLAnimeBulldozer_v20.safetensors
98
- _x44-kohakuXLGamma_rev2.safetensors
99
- _x45-awmo-xl.safetensors
100
- _x46-realvisxlV30Turbo_v30Bakedvae.safetensors
101
  ```
102
 
103
- </details>
104
-
105
- ### Selected models ###
106
-
107
- - `te0`: Models selected for using the **CLIP**, or `conditioner.embedders.0`.
108
-
109
- - `te1`: Models selected for using the **CLIP-AUX**, or `conditioner.embedders.1`.
110
-
111
- - `te2`: Models looks acceptable with both CLIPs applied. Not for selection, just for reference.
112
-
113
- - `=sd`: Models has the exact same CLIP pair as the original SDXL `_x25`.
114
 
115
- - `--` is used for placeholder because I need to figure out the model pairs to be merged.
116
 
117
- - Total / subtotal count will be shown as `=xx`.
 
 
 
118
 
119
- - `xxa` e.g. `09a` is the merge of `_x17` and `_x18`, because of model deviation. It introduce some error on expected model weight, but will be negligible when the scale is large.
120
 
121
  ```
122
- te0: --,--,03,05,--,10,11,--,--,16,17,09a,10a,20,11a,22,23,24,25,26,27,32,--,36,--,--,41,--=19
123
- te1: 01,02,03,05,06,10,--,12,14,16,17,09a,10a,20,11a,22,--,24,25,26,27,32,33,36,37,38,41,42=26
124
- te2: 01,--,03,05,06,10,--,--,--,16,17,09a,10a,20,11a,22,--,24,25,--,27,32,33,36,37,38,41,--=21
125
- =sd: --,--,03,--,--,10,--,12,--,16,--,-18,-19,--,---,--,--,--,25,--,--,--,--,--,--,--,--,--=7
126
- ```
127
- - Excluding the `=sd` for the actual merge will be shown below. Intermediate model name will be `x01te1-AstolfoMix-_x01_x02`.
128
 
129
- ```
130
- te0:--,--,05,--,11,--,--,17,20,11a,22,23,24,25,26,27,32,--,36,--,--,41,--=14
131
- te1:01,02,05,06,--,12,14,17,20,11a,22,--,24,25,26,27,32,33,36,37,38,41,42=21
132
  ```
133
 
134
- - `unet`: Models selected for using the UNET.
135
 
136
- - `nsfw`: Models selected for using the UNET. This time I used a NSFW prompt for test.
137
 
138
- - To keep it easy to trace (originaly it is 33 / 15), I adjust it to be a perfect 2^n. It will be handy for future merge, when new model appears.
139
 
140
- - `x01a`: Model pairs which are already available for merge. Therefore I can reuse for saving disk space, a lot.
 
 
 
 
 
141
 
142
- ```
143
- unet: 01,02,06,07,09,10,11,12,13,15,16,17,20,21,22,23,25,26,27,28,30,31,32,33,34,--,37,38,39,40,42,43,44=32
144
- nsfw: 01,--,06,07,--,--,11,12,13,15,--,--,20,21,22,23,--,--,27,--,--,31,--,--,--,36,--,--,--,40,--,43,--=16
145
- x01a: 01,02,--,--,09,10,11,12,--,15,16,--,--,21,22,--,25,26,27,28,--,31,32,33,34,--,37,38,39,40,--,43,44
146
- ```
147
- - Finally here is the result model name:
148
-
149
- ```
150
- base=x17-AstolfoMix-x13te0x14te1.safetensors
151
- nsfw=x11c-AstolfoMix-x13te0x14te1.safetensors
152
- ```
 
8
  - text-to-image
9
  - safetensors
10
  inference: true
11
+ thumbnail: https://huggingface.co/6DammK9/AstolfoMix-XL/resolve/main/240426-1841382272-2016-1152-4.5-256-20240418043456.png
12
  widget:
13
  - text: >-
14
  aesthetic, quality, 1girl, boy, astolfo
 
23
  - Unsolved merge, even with experience on [SD1](https://huggingface.co/6DammK9/AstolfoMix) and [SD2](https://huggingface.co/6DammK9/AstolfoMix-SD2).
24
  - See [full article in Github](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/README_XL.MD)
25
 
26
+ ## Extended-FP64 ##
27
 
28
+ - **Uniform merge** of 52 UNETS + (61+42) CLIPS (from 70 models discovered).
29
 
30
+ - Current version: `x51-AstolfoMix-x60te0x41te1-e2e-240407-feefbf4.safetensors`
31
+ - Recommended version: "x51"
32
+ - Recommended CFG: 4.5 (with CHG = 1.0), 3.0 (with PAG = 1.0)
33
  - *Prompt is minimal.*
34
 
35
+ ![240426-1841382272-2016-1152-4.5-256-20240418043456.png](https://huggingface.co/6DammK9/AstolfoMix-XL/resolve/main/240426-1841382272-2016-1152-4.5-256-20240418043456.png)
36
 
37
  ```
38
  parameters
39
 
40
+ (car:0), [[mclaren]], (1boy:0), [astolfo]
41
+ Steps: 256, Sampler: Euler, Schedule type: Automatic, CFG scale: 4.5, Seed: 1841382272, Size: 1344x768, Model hash: a52eba463d, Model: x51-AstolfoMix-x60te0x41te1-e2e-240407-feefbf4, VAE hash: 26cc240b77, VAE: sd_xl_base_1.0.vae.safetensors, Denoising strength: 0.7, Clip skip: 2, CHG: "{'RegS': 1, 'RegR': 1, 'MaxI': 50, 'NBasis': 0, 'Reuse': 1, 'Tol': -4, 'IteSS': 1, 'ASpeed': 0.4, 'AStrength': 0.5, 'AADim': 2, 'CMode': 'More ControlNet', 'StartStep': 0, 'StopStep': 1}", FreeU Stages: "[{\"backbone_factor\": 1.1, \"skip_factor\": 0.6}, {\"backbone_factor\": 1.2, \"skip_factor\": 0.4}]", FreeU Schedule: "0.0, 1.0, 0.0", FreeU Version: 2, Hires upscale: 1.5, Hires steps: 64, Hires upscaler: Latent, Dynamic thresholding enabled: True, Mimic scale: 1, Separate Feature Channels: False, Scaling Startpoint: MEAN, Variability Measure: AD, Interpolate Phi: 0.3, Threshold percentile: 100, Refiner switch by sampling steps: True, Version: v1.9.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  ```
43
 
44
+ ## Baseline ##
 
 
 
 
 
 
 
 
 
 
45
 
46
+ - **Uniform merge** of 32 UNETS + (19+26) CLIPS (from 21 models). Discovered model count: 42.
47
 
48
+ - Current version: `x17-AstolfoMix-x13te0x14te1.safetensors`
49
+ - Recommended version: "x17" for full experience, or "x11c" for human focused.
50
+ - Recommended CFG: 4.5
51
+ - *Prompt is minimal.*
52
 
53
+ ![240234-2213673007-2016-1152-4.5-192-20240210015331.jpg](https://huggingface.co/6DammK9/AstolfoMix-XL/resolve/main/240234-2213673007-2016-1152-4.5-192-20240210015331.jpg)
54
 
55
  ```
56
+ parameters
 
 
 
 
 
57
 
58
+ (solo:0), (boy:0), (qipao:0.98), [astolfo_\(fate\)], [[lunar new year]], [[[[kowloon]]]]
59
+ Steps: 192, Sampler: Euler, CFG scale: 4.5, Seed: 2213673007, Size: 1344x768, Model hash: 82f53a8fe1, Model: x17-AstolfoMix-x13te0x14te1, VAE hash: 26cc240b77, VAE: sd_xl_base_1.0.vae.safetensors, Denoising strength: 0.7, Clip skip: 2, FreeU Stages: "[{\"backbone_factor\": 1.1, \"skip_factor\": 0.6}, {\"backbone_factor\": 1.2, \"skip_factor\": 0.4}]", FreeU Schedule: "0.0, 1.0, 0.0", FreeU Version: 2, Hires upscale: 1.5, Hires upscaler: Latent, Dynamic thresholding enabled: True, Mimic scale: 1, Separate Feature Channels: False, Scaling Startpoint: MEAN, Variability Measure: AD, Interpolate Phi: 0.3, Threshold percentile: 100, Version: v1.7.0
 
60
  ```
61
 
62
+ ## Recipes / Model selection logs / Models involved ##
63
 
64
+ - See [full article in Github](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/README_XL.MD)
65
 
 
66
 
67
+ |Round|Model Name|RAW|UNET|TE0|TE1|Recipe|
68
+ |---|---|---|---|---|---|---|
69
+ |01|`x17-AstolfoMix-x13te0x14te1.safetensors`|42|32|14|21|[json](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/recipes/recipe-x39a.json)|
70
+ |02|`x43-AstolfoMix-x22te0x31te1.safetensors`|50|44|22|31|[mecha](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/recipes/x43-AstolfoMix-x21te0x30te1-e2e-240222-60d0764.mecha)|
71
+ |03|`x45-AstolfoMix-x39te0x39te1-e2e-240222-60d0764.safetensors`|52|46|40|40|[mecha](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/recipes/x45-AstolfoMix-x39te0x39te1-e2e-240222-60d0764.mecha)|
72
+ |04|`x63-AstolfoMix-x60te0x41te1-e2e-240407-feefbf4.safetensors`|70|52|61|42|[mecha](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/recipes/x63-AstolfoMix-x60te0x41te1-e2e-240407-feefbf4.mecha)|
73