Update README.md
Browse files
README.md
CHANGED
|
@@ -5,4 +5,5 @@ Hypernetwork trained on some Midjourney V4 portraits.
|
|
| 5 |
|
| 6 |
Euler a and DPM++ samplers work best. CFG scale at 7 and low step count (<50) work well.
|
| 7 |
|
| 8 |
-
Prompts should include words like "portrait", "octane render" and "highly detailed" for best results.
|
|
|
|
|
|
| 5 |
|
| 6 |
Euler a and DPM++ samplers work best. CFG scale at 7 and low step count (<50) work well.
|
| 7 |
|
| 8 |
+
Prompts should include words like "portrait", "octane render" and "highly detailed" for best results.
|
| 9 |
+
Avoid using face restoration like GFPGAN or CodeFormer if possible
|