Create README.md
Browse files- LongVie2/README.md +11 -0
LongVie2/README.md
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
LongVie2:
|
| 2 |
+
|
| 3 |
+
Source project: https://huggingface.co/Vchitect/LongVie2
|
| 4 |
+
|
| 5 |
+
`LongVie2_attn_layers_bf16.safetensors` replaces base I2V model's attention layers, can be used as extra_model, this ensures the full weights of the original.
|
| 6 |
+
|
| 7 |
+
`longvie2_attn_layers_lora_rank_64_bf16.safetensors` This is a LoRA extracted from the attention layer diff, slightly weaker effect than full weights but functional.
|
| 8 |
+
|
| 9 |
+
Use either of those, not both.
|
| 10 |
+
|
| 11 |
+
`LongVie2_dual_controller_controlnet_bf16.safetensor` is the controlnet model weights, loaded as extra_model in WanVideoWrapper and used with `Add Dual Control Embeds` -node
|