Pet Eating is a one-tap file, not a prompt you rewrite weekly

/templates is a photo in, a clip out. A new generate is a different object.

Pet Eating drops your pet into a cozy bed scene wearing a Garfield-style hoodie, eating lasagna while scrolling on a phone. Inputs: Your pet photo (user_image_url), required. Estimated cost on the card: about 68 credits (135 at the listed full rate). You do not rewrite a Veo prompt every Friday to chase the same gag. You attach the still the template already knows how to consume. You run it.

A blank generate — "make my dog eat lasagna in a hoodie, cinematic, cozy bed" — is a different SKU. Different bill. Different failure mode. The template already chose the stack. Your job is the photo.

One required still. The hoodie is already decided.

Run a one-tap AI video template is the named agent job. get_template lists the inputs. start_template_run starts when every required input is a hosted URL, usually a photo attached with the chat + button. A live card tracks the run. get_template_run and cancel_template_run support that card. You do not poll status in most cases. Output is that template's finished video.

Pet Eating has one image field and it is required. There is no default pet. Starting with a partial inputs object is how you get an error instead of a clip. Attach the pet still. Then start.

No timeline. No scene list. No "write a three-act lasagna." The creative choice happened when the template was built. Weekly novelty is a new photo, not a new paragraph.

Last week's prompt is a different SKU

People open a text-to-video row and paste last week's eating prompt with a new adjective. That is a generate. It will invent a face that is not the upload, a hoodie the still never wore, a breed the jpeg is not. It will also not be the 68-credit one-tap object. You paid a model to approximate a template you already have.

Forcing Pet Eating to be a product ad, a talking brand film, or a multi-scene movie is the other miss. Templates do not take a plot. Create a multi-scene AI movie is a different named job. Cloning a public workflow (recreate_public_template) is a different object again: saved, not auto-run. One-tap is finger-snap / mugshot / pet-eating class: photo in, clip out, no cloned scene graph.

If no template matches, generate. Do not run Pet Eating "just to have motion." You will pay the template estimate for a format you will not post.

The stack is already chosen

The template already chose its models. Asking for Veo versus Kling on a one-tap run is how you discover that this job does not expose that switch. If you needed to pick a row per shot, you wanted a generate or a movie, not Pet Eating.

Cost is the number on the template card, shown before you run. It is not a per-second cinematic meter you can talk down in the prompt. Cancel an in-flight run with cancel_template_run. Closing the chat is not a cancel.

Use it when the post is the cozy eating gag. Skip it when the post is a product, a talker, or a story. Rewrite nothing weekly except the still.

FAQ

Can I run Pet Eating without a pet photo?

No. user_image_url is required. Unlike templates that ship defaults for optional people fields, this format does not start until the pet still is a hosted URL.

Can I change the hoodie or the lasagna in the prompt?

Not as a one-tap. The format is fixed: Garfield-style hoodie, lasagna, phone, cozy bed. A new generate with a rewritten prompt is a different object — different cost, different face risk, no template card.

Is this a saved workflow I can rewrite the plot on?

No. Saved video workflows rewrite a plot around locked characters. Pet Eating does not write plots. It applies a format to your pet photo.

Can I swap Veo in so the lasagna looks more cinematic?

Then you are not in this template. Generate, and accept that you are no longer in the one-tap, ~68-credit, photo-in-clip-out path. Pick that on purpose.