Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,20 @@
|
|
| 1 |
---
|
| 2 |
license: creativeml-openrail-m
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: creativeml-openrail-m
|
| 3 |
+
tags:
|
| 4 |
+
- stable-diffusion
|
| 5 |
+
- stable-diffusion-diffusers
|
| 6 |
+
- text-to-image
|
| 7 |
---
|
| 8 |
+
|
| 9 |
+
# Counterfeit-V3.0
|
| 10 |
+
・I have utilized BLIP-2 as a part of the training process. Natural language prompts might be more effective.
|
| 11 |
+
・I prioritize the freedom of composition, which may result in a higher possibility of anatomical errors.
|
| 12 |
+
・The expressiveness has been improved by merging with negative values, but the user experience may differ from previous checkpoints.
|
| 13 |
+
・I have uploaded a new Negative Embedding, trained with Counterfeit-V3.0.
|
| 14 |
+
There's likely no clear superiority or inferiority between this and the previous embedding, so feel free to choose according to your preference.
|
| 15 |
+
Note that I'm not specifically recommending the use of this embedding.
|
| 16 |
+
|
| 17 |
+
# Sample image
|
| 18 |
+
prompt & Setting: https://civitai.com/models/4468/counterfeit-v30
|
| 19 |
+
|
| 20 |
+
|