Upload 2446218/3203205/h3_ride_template.txt with huggingface_hub
Browse files
2446218/3203205/h3_ride_template.txt
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
This is woman with purple skin having sex , riding on top .
|
| 2 |
+
|
| 3 |
+
Write description of video based on the provided image , make it interesting, fast paced or with unexpected ending. Base it on overall scene and mood. Try to use all or most characters from the image by using <Subject 1> , <Subject 2> (or more) in subject_definitions and then use (S1) , (S2) in integrated_multimodal_description to refer to them.
|
| 4 |
+
It should be written in this format:
|
| 5 |
+
|
| 6 |
+
(example start)
|
| 7 |
+
For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.
|
| 8 |
+
|
| 9 |
+
subject_definitions:
|
| 10 |
+
<Subject 1> Muscular elf man with blonde hair , wearing xyz or is naked.
|
| 11 |
+
<Subject 2> Woman, with dark hair , wearing xyz or is naked.
|
| 12 |
+
|
| 13 |
+
environment: Studio lighting with soft sun light in the forest matching <Picture 1> color temperature.
|
| 14 |
+
camera: Static medium portrait shot.
|
| 15 |
+
integrated_multimodal_description: (S1) slowly smiles, shows hit bot and blinks naturally. (S2) fixed her stance and comes closer to (S1) while smiling. Fast paced action shot.
|
| 16 |
+
|
| 17 |
+
overall_soundscape: Soft ambient breath sound, warm gentle acoustic melody.
|
| 18 |
+
|
| 19 |
+
non_diegetic_music: N/A
|
| 20 |
+
|
| 21 |
+
ending: (S1) shoots an arrow at a tree ,(S2) graceful claps her hands , while the camera settles on the arrow that was shot.
|
| 22 |
+
(example end)
|
| 23 |
+
|
| 24 |
+
Camera motion should be written as a natural English action within the shot, rather than stacked
|
| 25 |
+
as separate labels at the end of a sentence , examples:
|
| 26 |
+
"The camera pushes in with small amplitude at slow speed toward the folded letter in her hands."
|
| 27 |
+
"The camera pans right with large amplitude at fast speed, revealing the open doorway."
|
| 28 |
+
"The camera holds a static shot as the runner exits the frame."
|
| 29 |
+
|
| 30 |
+
If <Subject 1> <Subject 2> is mostly out of frame don't add description in integrated_multimodal_description just add interaction of S1 with "character outside the frame" if that's relevant to main scene.
|
| 31 |
+
|
| 32 |
+
Don't make "ending:" too long , most of action should happen in "integrated_multimodal_description:"
|
| 33 |
+
Reply only with formated text similar to provided example , use same format.
|
| 34 |
+
Remove "\n" from the text if those get added.
|
| 35 |
+
|