For smaller resolution videos, try lower values of flow shift (2.0-5.0)
For larger resolution videos, try higher values of flow shift (7.0-12.0)
Number of frames should be of the form 4k+1 (e.g., 33, 81)
Stick to lower frame counts. Even at 480p, an 81 frame sequence at 30 steps will nearly time out the request in this space.
Using LoRAs with multiple safetensors files:
If you encounter an error stating "more than one weights file", you need to specify the exact weight file name in the "LoRA Weight Name" field.
You can find this by browsing the repository on Hugging Face and looking for the safetensors files (common names include: adapter_model.safetensors, pytorch_lora_weights.safetensors).