neph1's picture
Update README.md
0030c36 verified
---
base_model:
- lllyasviel/FramePackI2V_HY
library_name: diffusers
---
Loras mentioned in this article: https://huggingface.co/blog/neph1/framepack-camera-control-loras
Trigger word for each is "cam_control".
Trigger and training prompts:
<li>rotate_360_500.safetensors - "cam_control", "The camera rotates 360 degrees around the subject."
<li>hero_zoom_500.safetensors - "hero_zoom", "the camera zooms in on the subjects face."
<li>cam_control_rotate_left_600.safetensors - "cam_control", "The camera rotates around the subject.
<li>cam_control_zoom_out.safetensors - "cam_control", "The camera zooms out while focusing on the subject."
If the training video bleeds through (like a grey cube appearing in the generation), lower the strength. Between 0.5 and 1.0
250605: Added two more loras
<p>
<img src="https://cdn-uploads.huggingface.co/production/uploads/653cd3049107029eb004f968/3lK7jfKRb1cLsMSpAiVLc.webp" alt="slow_zoom training video" width="368" style="display:inline-block; margin-right: 10px;">
<img src="https://cdn-uploads.huggingface.co/production/uploads/653cd3049107029eb004f968/PBYp1WDoPcfDxoehFy9Nn.webp" alt="slow_zoom result" width="368" style="display:inline-block; margin-right: 10px;">
</p>
Trigger word: slow_zoom.
<p>
<img src="https://cdn-uploads.huggingface.co/production/uploads/653cd3049107029eb004f968/48SVmT_InM4kyEHxymo-M.webp" alt="handheld_camera training video" width="368" style="display:inline-block; margin-right: 10px;">
<img src="https://cdn-uploads.huggingface.co/production/uploads/653cd3049107029eb004f968/u9kxuAayLbHXgo4VxH0SQ.webp" alt="handheld_camera result" width="368" style="display:inline-block; margin-right: 10px;">
</p>
Trigger word: handheld_camera (camera not guaranteed)