BudFactory
commited on
Commit
•
447d320
1
Parent(s):
8d34c64
Update README.md
Browse files
README.md
CHANGED
|
@@ -8,7 +8,7 @@ language:
|
|
| 8 |
---
|
| 9 |
I'll preface this by saying that I have no idea what I'm doing. Also, this is by no means a complete or perfect model. But after many tries I'm at a point where I'm happy with sharing some pictures and an early version for you to try out.
|
| 10 |
|
| 11 |
-
# Classic Negative
|
| 12 |
|
| 13 |
With Classic Negative I tried to train a model with DreamBooth which closely mimics my style of photography. Its name comes from a built in camera profile in Fujifilm cameras, "Classic Negative". I use a modified version of this profile in basically all of my photos. To mimic my style, the model must achieve the following:
|
| 14 |
|
|
@@ -32,11 +32,11 @@ The prompts I tried so far are very simple. The activation token is classicnegat
|
|
| 32 |
- classicnegative photo of a cute small red panda sitting on a branch in the jungle
|
| 33 |
- classicnegative photo of a white fluffy rabbit standing in a garden illuminated by fairy lights, winter, heavy snow, snowflakes
|
| 34 |
|
| 35 |
-
Parameters
|
| 36 |
|
| 37 |
I then went seed hunting. Although in a batch of 4 there was at least one usable picture so far. If a good picture was generated, I set the same seed and ran it again with Hires. fix enabled (which takes like 3,5 minutes with my GTX 1070 for one picture).
|
| 38 |
|
| 39 |
-
Hires. fix Parameters
|
| 40 |
|
| 41 |
I discovered this by accident, but using these settings the picture stays exactly the same and all the film photo characteristics like the grain won't get lost during upscaling.
|
| 42 |
If the effect of the model is too strong, try adding tokens like sharp focus, high contrast, clarity to your prompt. Or just increase the contrast in post. But yes, sometimes it becomes a bit too much, I'll have to take a look into it for a future revision.
|
|
|
|
| 8 |
---
|
| 9 |
I'll preface this by saying that I have no idea what I'm doing. Also, this is by no means a complete or perfect model. But after many tries I'm at a point where I'm happy with sharing some pictures and an early version for you to try out.
|
| 10 |
|
| 11 |
+
# Classic Negative (SD 1.5)
|
| 12 |
|
| 13 |
With Classic Negative I tried to train a model with DreamBooth which closely mimics my style of photography. Its name comes from a built in camera profile in Fujifilm cameras, "Classic Negative". I use a modified version of this profile in basically all of my photos. To mimic my style, the model must achieve the following:
|
| 14 |
|
|
|
|
| 32 |
- classicnegative photo of a cute small red panda sitting on a branch in the jungle
|
| 33 |
- classicnegative photo of a white fluffy rabbit standing in a garden illuminated by fairy lights, winter, heavy snow, snowflakes
|
| 34 |
|
| 35 |
+
**Parameters:** Euler A, CFG Scale 7, 30 Steps, 860x360px
|
| 36 |
|
| 37 |
I then went seed hunting. Although in a batch of 4 there was at least one usable picture so far. If a good picture was generated, I set the same seed and ran it again with Hires. fix enabled (which takes like 3,5 minutes with my GTX 1070 for one picture).
|
| 38 |
|
| 39 |
+
**Hires. fix Parameters:** ESRGAN_4x, 30 Steps, 0.3 Denoising, Upscale by 2
|
| 40 |
|
| 41 |
I discovered this by accident, but using these settings the picture stays exactly the same and all the film photo characteristics like the grain won't get lost during upscaling.
|
| 42 |
If the effect of the model is too strong, try adding tokens like sharp focus, high contrast, clarity to your prompt. Or just increase the contrast in post. But yes, sometimes it becomes a bit too much, I'll have to take a look into it for a future revision.
|