Request a Wan2.1 LoRA on our Discord and we will train and open-source it for free.
Join our Discord to generate videos of the Bride Transformation LoRA for free.
Wan2.1 14B I2V 480p v1.0:
Trained on 40 seconds of video comprised of 8 short clips (each clip captioned separately) of people undergoing a bride transformation. This was trained on the Wan.21 14B I2V 480p model.
The trigger word is: '8r1d3 bride 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. Find Kijai's original workflow here:
https://github.com/kijai/ComfyUI-WanVideoWrapper/blob/main/example_workflows/wanvideo_480p_I2V_example_02.json
Check out all our LoRAs on our page: https://app.remade.ai/
Prompt Examples:
The video begins with a portrait of a bunny rabbit, then the 8r1d3 bride effect occurs. The bunny rabbit is now in a white wedding dress, holding a bouquet, with a sunny, warm beige background.
The video begins with a portrait of a woman, then the 8r1d3 bride effect occurs. The woman is now in a white wedding dress, holding a bouquet, with a sunny, warm beige background.
The video starts with a close-up of a smiling man in a blue button-down shirt, then the 8r1d3 bride effect happens. The man is now in a white lace wedding dress, smiling, with a bouquet of white flowers in front of a blurred wooden background.
Let me know if there are any questions, I'll be happy to help!