Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,90 @@
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
---
|
| 4 |
+
EMA produces sharper images while MSE's images are smoother
|
| 5 |
+
|
| 6 |
+
____________________________________________________________________________
|
| 7 |
+
|
| 8 |
+
Sharing this model with the community. As it closely resembles Lexica Art V2 or Lexica Aperture v2, this product is an excellent choice.
|
| 9 |
+
|
| 10 |
+
It's absolutely amazing how we're able to create incredibly realistic faces with only a few simple steps.
|
| 11 |
+
|
| 12 |
+
If you want to support my work, you can buy me a coffee or tea:
|
| 13 |
+
|
| 14 |
+
https://ko-fi.com/gswan
|
| 15 |
+
|
| 16 |
+
https://www.buymeacoffee.com/gswan
|
| 17 |
+
|
| 18 |
+
Enhance your writing prompt by adding the estilovintedois prefix, as it guarantees a consistent writing style.
|
| 19 |
+
|
| 20 |
+
"While you're welcome to use this model, please keep in mind that any potential damages or mishaps resulting from its use are not our responsibility..."
|
| 21 |
+
|
| 22 |
+
"This model was trained on a large amount of high quality images with simple prompts to generate beautiful images without a lot of prompt engineering."
|
| 23 |
+
|
| 24 |
+
"It should also be very dreamboothable, being able to generate high fidelity faces with a little amount of steps."
|
| 25 |
+
|
| 26 |
+
This model is based on vintedois_diffusion. Credit to the original developers.
|
| 27 |
+
Vintedois (22h) Diffusion model trained by Predogl and piEsposito with open weights, configs and prompts (as it should be).
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
Example prompts
|
| 31 |
+
|
| 32 |
+
Prompt: photo of an old man in a jungle, looking at the camera
|
| 33 |
+
|
| 34 |
+
CFG Scale: 7.5
|
| 35 |
+
|
| 36 |
+
Scheduler: diffusers.EulerAncestralDiscreteScheduler
|
| 37 |
+
|
| 38 |
+
Steps: 30
|
| 39 |
+
|
| 40 |
+
Seed: 44
|
| 41 |
+
|
| 42 |
+
Prompt: kneeling cat knight, portrait, finely detailed armor, intricate design, silver, silk, cinematic lighting, 4k
|
| 43 |
+
|
| 44 |
+
CFG Scale: 7.5
|
| 45 |
+
|
| 46 |
+
Scheduler: diffusers.EulerAncestralDiscreteScheduler
|
| 47 |
+
|
| 48 |
+
Steps: 50
|
| 49 |
+
|
| 50 |
+
Seed: 44
|
| 51 |
+
|
| 52 |
+
Prompt: a beautiful girl In front of the cabin, the country, by Artgerm Lau and Krenz Cushart,hyperdetailed, trending on artstation, trending on deviantart
|
| 53 |
+
|
| 54 |
+
CFG Scale: 7.5
|
| 55 |
+
|
| 56 |
+
Scheduler: diffusers.EulerAncestralDiscreteScheduler
|
| 57 |
+
|
| 58 |
+
Steps: 50
|
| 59 |
+
|
| 60 |
+
Seed: 44
|
| 61 |
+
|
| 62 |
+
Prompt: destroyed city
|
| 63 |
+
|
| 64 |
+
CFG Scale: 7.5
|
| 65 |
+
|
| 66 |
+
Scheduler: diffusers.EulerAncestralDiscreteScheduler
|
| 67 |
+
|
| 68 |
+
Steps: 50
|
| 69 |
+
|
| 70 |
+
Seed: 44
|
| 71 |
+
|
| 72 |
+
Prompt: victorian city landscape
|
| 73 |
+
|
| 74 |
+
CFG Scale: 7.5
|
| 75 |
+
|
| 76 |
+
Scheduler: diffusers.EulerAncestralDiscreteScheduler
|
| 77 |
+
|
| 78 |
+
Steps: 50
|
| 79 |
+
|
| 80 |
+
Seed: 44
|
| 81 |
+
|
| 82 |
+
Prompt: prehistoric native living room
|
| 83 |
+
|
| 84 |
+
CFG Scale: 7.5
|
| 85 |
+
|
| 86 |
+
Scheduler: diffusers.EulerAncestralDiscreteScheduler
|
| 87 |
+
|
| 88 |
+
Steps: 50
|
| 89 |
+
|
| 90 |
+
Seed: 44
|