Generate videos with 100+ camera control and VFX LoRAs for free on the Remade Canvas.
Wan2.1 14B I2V 480p v1.0:
Trained on 50 seconds of video comprised of 10 short clips (each clip captioned separately) of scenes that used the crash zoom in camera motion.
The trigger phrase is: 'cr34sh crash zoom in effect'
See below for some prompt examples that worked well for me. You can also check the videos I've posted here for the captions that were used to generate them. For each video the input image is just the first frame.
Recommended Settings:
LoRA strength = 1.0
Embedded guidance scale = 6.0
Flow shift = 5.0
Here's a link to the Wan2.1 I2V LoRA inference workflow I used to generate these videos: https://huggingface.co/Remade/Squish/blob/main/workflow/wan_img2video_lora_workflow.json
This is a slight modification to Kijai's version, with the main difference being the addition of the WanVideo Lora Select node, connected to the 'lora' field of the WanVideo Lora Select node.
Prompt Examples:
A man with short brown hair wearing a white shirt and a dark coat stands in the red neon light of a motel room doorway. He looks back towards the motel room. The camera performs a cr34sh crash zoom in effect, rapidly zooming closer to the man's face. He turns with a shocked expression, as if he heard a noise, and reaches for his pocket.
A young woman with red hair in a ponytail, wearing a t-shirt and jeans, sits in a wooden chair, facing away from the camera, in a room filled with dozens of old CRT televisions, each displaying different images. The camera performs a cr34sh crash zoom in effect, rapidly zooming closer to the woman's face as she turns her head, looking directly at the viewer with a mixture of curiosity and confusion. The image on the central TV begins to change, reflecting the scene.
Let me know if there are any questions, I'll be happy to help!
You can also join our Discord to request LoRAs and generate videos with them for free!