Update README.md
Browse files
README.md
CHANGED
|
@@ -203,10 +203,11 @@ Im using small test set i have on me, separated into anime(434) and photo(500) i
|
|
| 203 |
| Anzhc MS-LC-EQ-D-VR VAE B5 | <span style="color:Orange">*5.8117*</span> | <span style="color:Orange">*9.7627*</span> | <span style="color:Orange">*29.8545*</span> | 0.1112 | <span style="color:Orange">*0.9538*</span> | 36.5573 | <span style="color:Orange">*0.0080*</span> | 4.963894 |
|
| 204 |
| Anzhc MS-LC-EQ-D-VR VAE B7 | <span style="color:Crimson">5.7046</span> | <span style="color:Crimson">9.5975</span> | <span style="color:Crimson">30.0106</span> | 0.0980 | <span style="color:Crimson">0.9553</span> | 39.4477 | <span style="color:Crimson">0.0071</span> | <span style="color:Crimson">4.017592</span> |
|
| 205 |
|
| 206 |
-
| VAE FLUX | L1 ↓ | L2 ↓ | PSNR ↑ | LPIPS ↓ | MS
|
| 207 |
-
|
| 208 |
-
| FLUX VAE |
|
| 209 |
-
| MS
|
|
|
|
| 210 |
|
| 211 |
|
| 212 |
#### Noise in latents
|
|
@@ -226,8 +227,9 @@ Im using small test set i have on me, separated into anime(434) and photo(500) i
|
|
| 226 |
|
| 227 |
| VAE FLUX | Noise ↓ |
|
| 228 |
|---|---|
|
| 229 |
-
| FLUX VAE |
|
| 230 |
| MS‑LC‑EQ‑D‑VR VAE FLUX | <span style="color:Crimson">7.635 |
|
|
|
|
| 231 |
|
| 232 |
---
|
| 233 |
### Results on a small benchmark of 434 Illustrations from Boorus
|
|
@@ -243,10 +245,11 @@ Im using small test set i have on me, separated into anime(434) and photo(500) i
|
|
| 243 |
| Anzhc MS-LC-EQ-D-VR VAE B5 | <span style="color:Orange">*4.0998*</span> | <span style="color:Orange">*7.5481*</span> | <span style="color:Orange">*31.4378*</span> | 0.0569 | <span style="color:Orange">*0.9717*</span> | 39.8600 | <span style="color:Orange">*0.0070*</span> | 5.178428 |
|
| 244 |
| Anzhc MS-LC-EQ-D-VR VAE B7 | <span style="color:Crimson">3.9949</span> | <span style="color:Crimson">7.3784</span> | <span style="color:Crimson">31.6544</span> | 0.0508 | <span style="color:Crimson">0.9731</span> | 42.8447 | <span style="color:Crimson">0.0063</span> | <span style="color:Crimson">4.216971</span> |
|
| 245 |
|
| 246 |
-
| VAE FLUX | L1 ↓ | L2 ↓ | PSNR ↑ | LPIPS ↓ | MS
|
| 247 |
-
|
| 248 |
-
| FLUX VAE |
|
| 249 |
-
| MS
|
|
|
|
| 250 |
|
| 251 |
|
| 252 |
#### Noise in latents
|
|
@@ -266,8 +269,9 @@ Im using small test set i have on me, separated into anime(434) and photo(500) i
|
|
| 266 |
|
| 267 |
| VAE FLUX | Noise ↓ |
|
| 268 |
|---|---|
|
| 269 |
-
| FLUX VAE |
|
| 270 |
| MS‑LC‑EQ‑D‑VR VAE FLUX | <span style="color:Crimson">7.723 |
|
|
|
|
| 271 |
|
| 272 |
KL loss suggests that this VAE implementation is much closer to SDXL, and likely will be a better candidate for further finetune, but that is just a theory.
|
| 273 |
|
|
|
|
| 203 |
| Anzhc MS-LC-EQ-D-VR VAE B5 | <span style="color:Orange">*5.8117*</span> | <span style="color:Orange">*9.7627*</span> | <span style="color:Orange">*29.8545*</span> | 0.1112 | <span style="color:Orange">*0.9538*</span> | 36.5573 | <span style="color:Orange">*0.0080*</span> | 4.963894 |
|
| 204 |
| Anzhc MS-LC-EQ-D-VR VAE B7 | <span style="color:Crimson">5.7046</span> | <span style="color:Crimson">9.5975</span> | <span style="color:Crimson">30.0106</span> | 0.0980 | <span style="color:Crimson">0.9553</span> | 39.4477 | <span style="color:Crimson">0.0071</span> | <span style="color:Crimson">4.017592</span> |
|
| 205 |
|
| 206 |
+
| VAE FLUX | L1 ↓ | L2 ↓ | PSNR ↑ | LPIPS ↓ | MS-SSIM ↑ | KL ↓ | CONSISTENCY ↓ | rFID ↓ |
|
| 207 |
+
|---|---|---|---|---|---|---|---|---|
|
| 208 |
+
| FLUX VAE | 4.1471 | 6.2940 | 33.3887 | <span style="color:Crimson">0.0209 | <span style="color:Orange">*0.9868* | 12.1461 | <span style="color:Orange">*0.0077* | <span style="color:Crimson">0.564150 |
|
| 209 |
+
| MS-LC-EQ-D-VR VAE FLUX | <span style="color:Orange">*3.799* | <span style="color:Orange">*6.077* | <span style="color:Orange">*33.807* | 0.032 | 0.986 | <span style="color:Crimson">10.992 | — | 1.692 |
|
| 210 |
+
| Flux EQ v2 B1 | <span style="color:Crimson">3.4560 | <span style="color:Crimson">5.5851 | <span style="color:Crimson">34.6641 | <span style="color:Orange">*0.0281* | <span style="color:Crimson">0.9884 | <span style="color:Orange">*11.4340* | <span style="color:Crimson">0.0040 | <span style="color:Orange">*0.686061* |
|
| 211 |
|
| 212 |
|
| 213 |
#### Noise in latents
|
|
|
|
| 227 |
|
| 228 |
| VAE FLUX | Noise ↓ |
|
| 229 |
|---|---|
|
| 230 |
+
| FLUX VAE | 10.499 |
|
| 231 |
| MS‑LC‑EQ‑D‑VR VAE FLUX | <span style="color:Crimson">7.635 |
|
| 232 |
+
| Flux EQ v2 B1 | <span style="color:Orange">*8.5019* |
|
| 233 |
|
| 234 |
---
|
| 235 |
### Results on a small benchmark of 434 Illustrations from Boorus
|
|
|
|
| 245 |
| Anzhc MS-LC-EQ-D-VR VAE B5 | <span style="color:Orange">*4.0998*</span> | <span style="color:Orange">*7.5481*</span> | <span style="color:Orange">*31.4378*</span> | 0.0569 | <span style="color:Orange">*0.9717*</span> | 39.8600 | <span style="color:Orange">*0.0070*</span> | 5.178428 |
|
| 246 |
| Anzhc MS-LC-EQ-D-VR VAE B7 | <span style="color:Crimson">3.9949</span> | <span style="color:Crimson">7.3784</span> | <span style="color:Crimson">31.6544</span> | 0.0508 | <span style="color:Crimson">0.9731</span> | 42.8447 | <span style="color:Crimson">0.0063</span> | <span style="color:Crimson">4.216971</span> |
|
| 247 |
|
| 248 |
+
| VAE FLUX | L1 ↓ | L2 ↓ | PSNR ↑ | LPIPS ↓ | MS-SSIM ↑ | KL ↓ | CONSISTENCY ↓ | rFID ↓ |
|
| 249 |
+
|---|---|---|---|---|---|---|---|---|
|
| 250 |
+
| FLUX VAE | 3.0600 | <span style="color:Orange">*4.7752* | <span style="color:Orange">*35.4400* | <span style="color:Crimson">0.0112 | <span style="color:Orange">*0.9905* | 12.4717 | <span style="color:Orange">*0.0079* | <span style="color:Crimson">0.669906 |
|
| 251 |
+
| MS-LC-EQ-D-VR VAE FLUX | <span style="color:Orange">*2.933* | 4.856 | 35.251 | 0.018 | 0.990 | <span style="color:Crimson">11.225 | — | 1.561 |
|
| 252 |
+
| Flux EQ v2 B1 | <span style="color:Crimson">2.4825 | <span style="color:Crimson">4.2776 | <span style="color:Crimson">36.6027 | <span style="color:Orange">*0.0132* | <span style="color:Crimson">0.9916 | <span style="color:Orange">*11.6388* | <span style="color:Crimson">0.0039 | <span style="color:Orange">*0.744904* |
|
| 253 |
|
| 254 |
|
| 255 |
#### Noise in latents
|
|
|
|
| 269 |
|
| 270 |
| VAE FLUX | Noise ↓ |
|
| 271 |
|---|---|
|
| 272 |
+
| FLUX VAE | 9.913 |
|
| 273 |
| MS‑LC‑EQ‑D‑VR VAE FLUX | <span style="color:Crimson">7.723 |
|
| 274 |
+
| Flux EQ v2 B1 | <span style="color:Orange">*8.4004* |
|
| 275 |
|
| 276 |
KL loss suggests that this VAE implementation is much closer to SDXL, and likely will be a better candidate for further finetune, but that is just a theory.
|
| 277 |
|