Type | |
Stats | 110 17 69 |
Reviews | (22) |
Published | May 5, 2025 |
Base Model | |
Training | Steps: 3,900 Epochs: 2 |
Usage Tips | Clip Skip: 2 Strength: 0.9 |
Trigger Words | the composition of frame-in-a-Frame |
Hash | AutoV2 0BF7315937 |
I'm a big movie fan. Thanks to the stable output of FLUX, some wonderful movie scenes can be reproduced. That's why I've decided to create this new series. I hope you'll like it.
1. Frame In a Frame
A frame within a frame is the use of visual elements in a scene to border a subject, further drawing the focus to them. The first frame is the literal shape and border of the entire image. The second frame is then created within the image, hence the term. To create this additional frame, photographers and cinematographers often use windows, doors, or other foreground elements. Subjects can also be framed with background elements that create the shape around the subject. It does not always have to be rectangular or square, just a shape that borders a subject.
Recommended Configuration
This LoRA has undergone extensive testing, and the example images are all generated in one go and have not undergone enlargement processing.
Weight: 0.6 - 1.5 (default 0.9)
Size: 768/1024/1536 (default 1024)
Guidance Condition: 2.5 - 3.5 (default 3.5)
Steps: 20 - 40 (compatible with the turbo acceleration model, default 8 steps)
Sampler: euler (simple)
Support WebUI/ComfyUI. After testing, the effect of ComfyUI is better. It is recommended to use it together with my workflow.
OK! The above is all the content for this time. If you have any questions, welcome to leave a message/return pictures/like/follow. It would be great to have a combo of all these actions.