Remove method illustration and caption
Browse files
README.md
CHANGED
|
@@ -19,11 +19,6 @@ tags:
|
|
| 19 |
- cuda
|
| 20 |
---
|
| 21 |
|
| 22 |
-
<div align="center">
|
| 23 |
-
<img src="vtm-elf-method.png" alt="Pose keypoints to torso character output (illustration)" width="100%"/>
|
| 24 |
-
<p><em>Illustration only — not actual model output quality. Model targets torso-up characters.</em></p>
|
| 25 |
-
</div>
|
| 26 |
-
|
| 27 |
# VTM-Elf 0.01
|
| 28 |
|
| 29 |
Pose-conditioned character generation for VTuber pipelines.
|
|
@@ -87,7 +82,6 @@ ckpt = hf_hub_download(
|
|
| 87 |
| File | Description |
|
| 88 |
|---|---|
|
| 89 |
| `VTM-elf.pt-000060000` | DiT-30M weights (step 60k) |
|
| 90 |
-
| `vtm-elf-method.png` | Illustration (not real output quality) |
|
| 91 |
| `README.md` | This card |
|
| 92 |
|
| 93 |
Runtime code for live camera → keypoints → inference is separate from this weight repo.
|
|
|
|
| 19 |
- cuda
|
| 20 |
---
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
# VTM-Elf 0.01
|
| 23 |
|
| 24 |
Pose-conditioned character generation for VTuber pipelines.
|
|
|
|
| 82 |
| File | Description |
|
| 83 |
|---|---|
|
| 84 |
| `VTM-elf.pt-000060000` | DiT-30M weights (step 60k) |
|
|
|
|
| 85 |
| `README.md` | This card |
|
| 86 |
|
| 87 |
Runtime code for live camera → keypoints → inference is separate from this weight repo.
|