Commit
·
4f5b604
1
Parent(s):
9245fa1
Remove redundant workflow overhead lines from README
Browse filesCo-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
README.md
CHANGED
|
@@ -22,7 +22,6 @@ Trained on **30,000 generated videos** spanning a wide range of subjects, styles
|
|
| 22 |
- **Improved image fidelity** -- the generated video maintains stronger adherence to the source image with less drift or distortion across frames.
|
| 23 |
- **Better motion coherence** -- subjects move more naturally and consistently throughout the clip.
|
| 24 |
- **Broader generalization** -- performs well across diverse subjects and scenes without needing per-category tuning.
|
| 25 |
-
- **Zero-workflow overhead** -- no ControlNet, no IP-Adapter stacking, no image manipulation required. Load the LoRA, attach an image embedding, prompt, and generate.
|
| 26 |
|
| 27 |
### A Note on Audio
|
| 28 |
|
|
@@ -36,8 +35,6 @@ Audio was **not** explicitly trained into this LoRA. However, due to the nature
|
|
| 36 |
4. Connect an **image embedding** node with your source image.
|
| 37 |
5. Add your text prompt and generate.
|
| 38 |
|
| 39 |
-
No additional nodes, preprocessing steps, or auxiliary models are needed.
|
| 40 |
-
|
| 41 |
### Workflow
|
| 42 |
|
| 43 |
|
|
|
|
| 22 |
- **Improved image fidelity** -- the generated video maintains stronger adherence to the source image with less drift or distortion across frames.
|
| 23 |
- **Better motion coherence** -- subjects move more naturally and consistently throughout the clip.
|
| 24 |
- **Broader generalization** -- performs well across diverse subjects and scenes without needing per-category tuning.
|
|
|
|
| 25 |
|
| 26 |
### A Note on Audio
|
| 27 |
|
|
|
|
| 35 |
4. Connect an **image embedding** node with your source image.
|
| 36 |
5. Add your text prompt and generate.
|
| 37 |
|
|
|
|
|
|
|
| 38 |
### Workflow
|
| 39 |
|
| 40 |
|