Update README.md
Browse files
README.md
CHANGED
|
@@ -18,4 +18,13 @@ CausVid 1.3B: https://huggingface.co/tianweiy/CausVid
|
|
| 18 |
|
| 19 |
AccVideo: https://huggingface.co/aejion/AccVideo-WanX-T2V-14B
|
| 20 |
|
| 21 |
-
Phantom: https://huggingface.co/bytedance-research/Phantom
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
AccVideo: https://huggingface.co/aejion/AccVideo-WanX-T2V-14B
|
| 20 |
|
| 21 |
+
Phantom: https://huggingface.co/bytedance-research/Phantom
|
| 22 |
+
|
| 23 |
+
---
|
| 24 |
+
CausVid LoRAs are experimental extractions from the CausVid finetunes, the aim with them is to benefit from the distillation in CausVid, rather than any actual causal inference.
|
| 25 |
+
---
|
| 26 |
+
v1 = direct extraction, has adverse effects on motion and introduces flashing artifact at full strength.
|
| 27 |
+
|
| 28 |
+
v1.5 = same as above, but without the first block which fixes the flashing at full strength.
|
| 29 |
+
|
| 30 |
+
v2 = further pruned version with only attention layers and no first block, fixes flashing and retains motion better, needs more steps and can also benefit from cfg.
|