wavymulder
commited on
Commit
•
c774458
1
Parent(s):
67de8e7
Update README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,8 @@
|
|
1 |
---
|
2 |
license: creativeml-openrail-m
|
3 |
---
|
|
|
|
|
4 |
Created this LoRA as a first test of training with FLUX.1-dev - thank you to [fal.ai](https://fal.ai/) for providing the compute!
|
5 |
|
6 |
Trained with activation token `ASCII art` but I recommend using this entire prompt schema for best effect: `ASCII art on a white background, made of letters, numbers, and other symbols, dithering effect,`
|
@@ -9,4 +11,7 @@ To test this LoRA, I used this workflow. Flux Guidance of 3.5, euler 40 steps, u
|
|
9 |
|
10 |
Obviously, it's not perfect ASCII. I'm still impressed with the performance VS previous test models trained on SDXL and SD1.5. Hit rate can be prompt dependent.
|
11 |
|
12 |
-
Also available on [Civit.ai](https://civitai.com/models/648623?modelVersionId=725667)
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: creativeml-openrail-m
|
3 |
---
|
4 |
+
![Header](https://huggingface.co/wavymulder/ASCII-flux-LoRA/resolve/main/images/ascii%20lora%20comp1.jpg?)
|
5 |
+
|
6 |
Created this LoRA as a first test of training with FLUX.1-dev - thank you to [fal.ai](https://fal.ai/) for providing the compute!
|
7 |
|
8 |
Trained with activation token `ASCII art` but I recommend using this entire prompt schema for best effect: `ASCII art on a white background, made of letters, numbers, and other symbols, dithering effect,`
|
|
|
11 |
|
12 |
Obviously, it's not perfect ASCII. I'm still impressed with the performance VS previous test models trained on SDXL and SD1.5. Hit rate can be prompt dependent.
|
13 |
|
14 |
+
Also available on [Civit.ai](https://civitai.com/models/648623?modelVersionId=725667)
|
15 |
+
|
16 |
+
![Image](https://huggingface.co/wavymulder/ASCII-flux-LoRA/resolve/main/images/ascii%20lora%20comp2.jpg?)
|
17 |
+
![Image](https://huggingface.co/wavymulder/ASCII-flux-LoRA/resolve/main/images/ascii%20lora%20comp3.jpg?)
|