Card: benchmark table transposed, total time per image
Browse files
README.md
CHANGED
|
@@ -43,17 +43,22 @@ Outside those settings the head still decodes; quality there is unmeasured.
|
|
| 43 |
|
| 44 |
## Measured
|
| 45 |
|
| 46 |
-
RTX 5070 Ti, 16 prompts at ~1 MP, compiled DiT blocks, one seed. PSNR is head vs the
|
| 47 |
-
decode of the same final latent.
|
|
|
|
| 48 |
|
| 49 |
-
|
|
| 50 |
-
|---|---|---|
|
| 51 |
-
|
|
| 52 |
-
|
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
|
| 58 |
Held-out reads during training (dB, colour / mono):
|
| 59 |
|
|
|
|
| 43 |
|
| 44 |
## Measured
|
| 45 |
|
| 46 |
+
RTX 5070 Ti, 16 prompts at ~1 MP, compiled DiT blocks, one seed; medians. PSNR is head vs the
|
| 47 |
+
VAE decode of the same final latent. "VAE, moved" is the usual interactive path: the VAE waits on
|
| 48 |
+
the CPU and goes to the card for the decode.
|
| 49 |
|
| 50 |
+
| | turbo, 4 steps, CFG 1 | base, Euler 28 + Spectrum, CFG 4 |
|
| 51 |
+
|---|---|---|
|
| 52 |
+
| DiT sampling | 0.97 s | 6.74 s |
|
| 53 |
+
| decode, pixel head | 7 ms | 14 ms |
|
| 54 |
+
| decode, VAE resident | 141 ms | 141 ms |
|
| 55 |
+
| decode, VAE moved CPU↔GPU | 176 ms | 179 ms |
|
| 56 |
+
| decode, VAE loaded from disk | 851 ms | 796 ms |
|
| 57 |
+
| decode peak VRAM above the DiT, head / VAE | 0.24 / 1.30 – 1.38 GB | 0.24 / 1.30 – 1.38 GB |
|
| 58 |
+
| head vs VAE | 35.4 dB | 33.0 dB |
|
| 59 |
+
| **total per image (DiT + decode), head vs VAE moved** | **0.98 s vs 1.15 s (1.17×)** | **6.75 s vs 6.92 s (1.02×)** |
|
| 60 |
+
|
| 61 |
+
Text encoding (~0.3 s per prompt) is outside the totals.
|
| 62 |
|
| 63 |
Held-out reads during training (dB, colour / mono):
|
| 64 |
|