ehristoforu commited on
Commit
00281ba
1 Parent(s): 2ca6af1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +100 -1
README.md CHANGED
@@ -1,3 +1,102 @@
1
  ---
2
- license: creativeml-openrail-m
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: other
3
+ license_name: fluently-license
4
+ license_link: https://huggingface.co/spaces/fluently/License
5
+ library_name: diffusers
6
+ pipeline_tag: image-to-image
7
+ base_model: runwayml/stable-diffusion-v1-5
8
+ tags:
9
+ - safetensors
10
+ - stable-diffusion
11
+ - sd1.5
12
+ - fluently
13
+ inference:
14
+ parameters:
15
+ num_inference_steps: 30
16
+ guidance_scale: 5.5
17
+ negative_prompt: >-
18
+ (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong
19
+ anatomy, extra limb, missing limb, floating limbs, (mutated hands and
20
+ fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting,
21
+ blurry, amputation
22
  ---
23
+
24
+ # **Fluently** - one model for all tasks ([Fluently XL](https://huggingface.co/fluently/Fluently-XL-v1))
25
+
26
+
27
+ *Special inpaint version, needed for small parts and complex objects.*
28
+
29
+
30
+ I would like to introduce my model - **Fluently**! This model was made by merging. I crossed a lot of checkpoints and loras.
31
+
32
+ ## About this model
33
+
34
+ In a nutshell, I took a few checkpoints and a bunch of Loras, I crossed through an extension in AUTOMATIC1111 - SuperMerger (available in extensions). Many factors were taken into account such as: eye quality, correct anatomy, reductions in required promt for a good result.
35
+
36
+ ### What makes my model different from others
37
+
38
+ - Correct anatomy: my model has the correct anatomy
39
+
40
+ - Face details: my model generates beautifully detailed faces and eyes even without AfterDetailer
41
+
42
+ - Artistic: my model activates beautiful artistry when it needs it
43
+
44
+ - Inpainting: my model is pretty good at Inpainting/Outpainting and I don't need to put in a specially designed model
45
+
46
+ - Anime & Comic Book style: my model can draw great Anime and Comic Book art
47
+
48
+ ### Merge details
49
+
50
+ Below is a severely truncated list of models and loras of this model merging:
51
+
52
+ *Models*:
53
+
54
+ - Juggernaut Final
55
+
56
+ - Deliberate V2
57
+
58
+ - RPG
59
+
60
+ - Realistic Vision V1.3
61
+
62
+ - DreamDrop V1
63
+
64
+ and more models...
65
+
66
+ *Loras*:
67
+
68
+ - LowRA V2
69
+
70
+ - Intricate Details
71
+
72
+ - Detail Slider
73
+
74
+ - Xeno Detailer
75
+
76
+ and more loras...
77
+
78
+ ## How to use this model
79
+
80
+ ### Quick Start
81
+
82
+ 1. Install this model and start the AUTOMATIC1111
83
+
84
+ 2. Select this checkpoint
85
+
86
+ 3. Generate images!
87
+
88
+ #### Optimal Parameters
89
+
90
+ - Steps: 20-30
91
+
92
+ - Sampler: DPM++ 2M Karras/Euler a
93
+
94
+ - CFG Scale: 5-7
95
+
96
+ - CLIP-skip: 1
97
+
98
+ - Negative Prompt: practically unnecessary
99
+
100
+ #### Addion for this model
101
+
102
+ style.csv for this model: [click](https://drive.google.com/file/d/1KZrWX66A2byBAdtcVPkBTMU0g00Hm6Ta/view?usp=sharing)