Process
Techniques
img2img
img2vid
Details in the post for this videotxt2img
Generation data
Resources used
- Checkpoint
Comfy
- Checkpoint
v2
- Checkpoint
DaSiWa Hybrid Turbo v3
Prompt
External Generator
Picture 1 shows the first frame. A neon city street and a ramen stall with a police woman and shop keeper.
Picture 2 is a close-up of the woman's face.
Picture 3 is a close-up of the ramen.
Audio 1 is how the muffled background music sounds.
S1 is the police woman standing in front of the stall shown in Picture 1 and Picture 2, she has glossy cybernetic metallic collarbones and arms.
S2 is the bowl of ramen she's eating shown in Picture 1 and Picture 3
S3 is the shop keeper shown in Picture 1 and Picture 3
Over the distant music of Audio 1, you hear loud urban noises and constant people talking, unintelligible.
[Shot 1] Loud unintelligible talking noises from the people outside. S3 is working and making more noodles. S1 bends over towards the ramen bowl S2.
[Shot 2] Camera jumps to close-up. People still talking. S1 brings the chopsticks up to her mouth and slurps her ramen. She tucks her hair behind her ear with the other hand. Wet slurping in ASMR stereo.
Other metadata
steps:8
Discussion


