Update README.md
Browse files
README.md
CHANGED
|
@@ -20,15 +20,6 @@ Open reference model for **video scene text editing**. Augments Wan2.1-VACE-14B
|
|
| 20 |
|
| 21 |
> Anonymous release under double-blind review at NeurIPS 2026 Datasets and Benchmarks Track. Author list and DOI updated after deanonymization.
|
| 22 |
|
| 23 |
-
## Specs
|
| 24 |
-
|
| 25 |
-
| | |
|
| 26 |
-
|---|---|
|
| 27 |
-
| Trainable parameters | 4.02 B (VACE blocks + new modules) |
|
| 28 |
-
| New modules | 971 M (GlyphEncoder + 8 × ConditionCrossAttention) |
|
| 29 |
-
| Total inference params | ~24 B (DiT 18.3 B + T5-XXL 5.7 B + Wan VAE 0.13 B) |
|
| 30 |
-
| Resolution / frames / fps | 1280 × 720 / 121 / 24 |
|
| 31 |
-
| Hardware | 1 × NVIDIA H100 / A100 80 GB (~70 GB VRAM) |
|
| 32 |
|
| 33 |
## Repository
|
| 34 |
|
|
|
|
| 20 |
|
| 21 |
> Anonymous release under double-blind review at NeurIPS 2026 Datasets and Benchmarks Track. Author list and DOI updated after deanonymization.
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
## Repository
|
| 25 |
|