Update README.md
Browse files
README.md
CHANGED
|
@@ -46,15 +46,22 @@ license: mit
|
|
| 46 |
## Model description
|
| 47 |
|
| 48 |
Trained locally with 20 publicly accessible images using AI-Toolkit (Flux.1 Dev).
|
|
|
|
| 49 |
Use with LoRA strength between **0.8-1.2** and FluxGuidance between **3-4**. No keywords needed.
|
|
|
|
| 50 |
Example prompt (ComfyUI): *Portrait photo of a woman in a garden.*
|
|
|
|
| 51 |
**Want a custom/private LoRA?** Good news—commissions are open! Request yours here: https://ko-fi.com/de_zoomer/commissions.
|
| 52 |
|
| 53 |
## Background
|
| 54 |
I've been deeply exploring how to create LoRAs with 100% accuracy to the original character. My focus is on quality, which is why my files tend to be heavier than others.
|
|
|
|
| 55 |
After creating over 100+ LoRAs for testing, using both Kohya and AI-Toolkit since day one, I've consistently stayed up to date with the latest releases, exchanging knowledge in their communities.
|
|
|
|
| 56 |
My expertise is mainly with characters, so I’m not as familiar with LoRAs for style or anime, although the process might not differ too much.
|
|
|
|
| 57 |
If you want your own custom LoRa, feel free to message me! Commissions are open—check out my Ko-fi link above.
|
|
|
|
| 58 |
Enjoy using my LoRAs and have fun!
|
| 59 |
|
| 60 |
## Download model
|
|
|
|
| 46 |
## Model description
|
| 47 |
|
| 48 |
Trained locally with 20 publicly accessible images using AI-Toolkit (Flux.1 Dev).
|
| 49 |
+
|
| 50 |
Use with LoRA strength between **0.8-1.2** and FluxGuidance between **3-4**. No keywords needed.
|
| 51 |
+
|
| 52 |
Example prompt (ComfyUI): *Portrait photo of a woman in a garden.*
|
| 53 |
+
|
| 54 |
**Want a custom/private LoRA?** Good news—commissions are open! Request yours here: https://ko-fi.com/de_zoomer/commissions.
|
| 55 |
|
| 56 |
## Background
|
| 57 |
I've been deeply exploring how to create LoRAs with 100% accuracy to the original character. My focus is on quality, which is why my files tend to be heavier than others.
|
| 58 |
+
|
| 59 |
After creating over 100+ LoRAs for testing, using both Kohya and AI-Toolkit since day one, I've consistently stayed up to date with the latest releases, exchanging knowledge in their communities.
|
| 60 |
+
|
| 61 |
My expertise is mainly with characters, so I’m not as familiar with LoRAs for style or anime, although the process might not differ too much.
|
| 62 |
+
|
| 63 |
If you want your own custom LoRa, feel free to message me! Commissions are open—check out my Ko-fi link above.
|
| 64 |
+
|
| 65 |
Enjoy using my LoRAs and have fun!
|
| 66 |
|
| 67 |
## Download model
|