Save this prompt as a fill-in template:
Use the attached image as the canonical visual anchor and generate a 3x3 storyboard shot burst in 21:9.
Preserve the exact [AESTHETIC], [COLOUR PALETTE], [LIGHTING], [MOOD], [SUBJECT DESIGN], and [ENVIRONMENT] from the source image.
Create 9 distinct frames from the same scene, exploring [SHOT TYPES]. Keep the composition [COMPOSITION STYLE], with [NEGATIVE SPACE LEVEL], [CAMERA CHARACTER], and [ATMOSPHERIC QUALITY]. No text, no labels, no redesign, no extra characters.
The result should feel like a cinematographer’s contact sheet from the same film scene.
Example variables:
[AESTHETIC] = minimalist mythic surrealism
[SHOT TYPES] = extreme wide, profile, close-up, overhead, low angle, detail shot
[COMPOSITION STYLE] = precise, geometric, restrained
[NEGATIVE SPACE LEVEL] = heavy
[CAMERA CHARACTER] = elegant, patient, controlled
[ATMOSPHERIC QUALITY] = hazy, quiet, cinematic
I've been chasing this for ages,
Expand a frame from my favourite aesthetic models while keeping the exact visual language, colour palette, composition style, mood, and worldbuilding is much harder.
I think I'm finally getting somewhere with GPT Image 2
prompt in next post
@Voidztar yea, I started with Kling too, I've find it's still really good particularly shots where subject is still, or locked off camera shots, means I can use it for simple shots instead of seedance to avoid queues and costs
Been playing with Krea 2.
Trained a LoRA on a few cool-toned Wes Anderson shots, then threw it into a blender with random moodboards and prompts for "a scene from a surreal and impossible fantasy movies"
No real objective. Just exploring the edges of the aesthetic.
Some random favourites and link to moodboard..
https://t.co/EVhzzwpwy2