360 Orbit LoRA for Wan2.1 14B I2V 480p
Overview
This LoRA is trained on the Wan2.1 14B I2V 480p model.It circles the camera smoothly around the subject, offering a full rotating view that adds energy and dimension. Ideal for dramatic reveals, product highlights, or showcasing a subject from all angles.
Features
- Trained on the Wan2.1 14B 480p I2V base model
- Consistent results across different object types
- Simple prompt structure that's easy to adapt
Community
- Generate videos with 100+ Camera Control and VFX LoRAs on the Remade Canvas.
- Discord: Join our community to generate videos with this LoRA for free
- Prompt
- A biker, with a red bandana and black leather jacket, sits astride a motorcycle in a workshop. He looks at the camera with a serious expression. The camera performs an 0rb4it 360 degree orbit, circling around him and the motorcycle, showing the workshop interior including tools, before returning to the front view. Throughout the 0rb4it 360 degree orbit, the biker remains seated on the bike.
- Prompt
- The video shows a meticulously assembled burger with floating ingredients. As the camera smoothly performs an 0rb4it 360 degree orbit, each element of the burger – the bun, lettuce, tomato slices, pickles, onion rings, bacon, cheese, and patty – slowly descends into place, one by one, to finish the burger. The camera completes the full rotation around the object
- Prompt
- An elderly woman with a headscarf and a walking stick stands in a stone alleyway. The camera performs an 0rb4it 360 degree orbit, moving from the front towards the woman's profile, then passing her back, revealing the stone buildings in the background as it circles. As the camera moves, the woman slowly takes a step forward, continuing her walk.
Model File and Inference Workflow
📥 Download Links:
- 360_Orbit.safetensors - LoRA Model File
- wan_img2vid_lora_workflow.json - Wan I2V with LoRA Workflow for ComfyUI
Recommended Settings
- LoRA Strength: 1.0
- Embedded Guidance Scale: 6.0
- Flow Shift: 5.0
Trigger Words
The key trigger phrase is: 0rb4it 360 degree orbit
Prompt Template
For prompting, check out the example prompts; this way of prompting seems to work very well.
ComfyUI Workflow
This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

See the Downloads section above for the modified workflow.
Model Information
The model weights are available in Safetensors format. See the Downloads section above.
Training Details
- Base Model: Wan2.1 14B I2V 480p
- Training Data: Trained on 50 seconds of video comprised of 10 short clips (each clip captioned separately) of the camera moving around various objects.
- Epochs: 30
Additional Information
Training was done using Diffusion Pipe for Training
Acknowledgments
Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!
- Downloads last month
- 729
Model tree for Remade-AI/360-Orbit
Base model
Wan-AI/Wan2.1-I2V-14B-480P