p-image

Prerequisites

Install and load these skills before generating (skip if already in context via @pruna):

Or install the full suite once: npx skills add PrunaAI/pruna-skills@pruna -y

Follow each skill's Before generating / craft sections — do not restate guide content here.

Agent habit

Routing: Use `p-image` for simple, quick photo generation from a short prompt. When photo generation needs more control (text in the image, structured JSON with hex/bbox, high-detail photoreal), use `p-image-ideogram` (defaults thinking: high, prompt_upsampling: true; low + prompt_upsampling: false + explicit prompt for a faster pass on the same model). For edits or video, use `p-image-edit` or `p-video-2` — not a new photo generation re-roll.

In the first reply, name `p-image` in backticks, confirm PRUNA_API_KEY is set (or stop with signup links from pruna-api), then ask for prompt / aspect ratio (open intake → generation-diversity clarification intake). When drafting the prompt, follow Prompt craft (dynamic + faithful) — do not paste skill examples.

Prompt craft (dynamic + faithful)

Every input.prompt must be fresh and specific, and must keep the user's request. Diversity never overrides the brief.

Fidelity check (before pay): if you remove the user’s named subject/product/setting from the prompt, the job is wrong — rewrite. Free axes only fill what the brief left open.

When showing a drafted prompt, still name `p-image` (guides help craft; this tool owns the call).

Pruna note: p-image has no prompt upsampling — concrete language is the whole craft. Avoid dense readable typography unless the user explicitly asked for copy on a surface.

When NOT to use

Use a different skill instead:

HTTP (curl)

Create (async — recommended)

curl -X POST 'https://api.pruna.ai/v1/predictions' \
  -H 'Content-Type: application/json' \
  -H "apikey: ${PRUNA_API_KEY}" \
  -H 'Model: p-image' \
  -d '{
    "input": {
      "prompt": "Disco ball reflections on an otter DJ scratching vinyl at a packed 1970s roller rink, fish-eye lens, glitter confetti mid-air, funky energy",
      "aspect_ratio": "9:16"
    }
  }'

Poll and download: follow pruna-api.

Complete the random seed ritual from generation-diversity before writing prompts — do not pass the ritual string as API seed. Optional api_seed only when the user requests reproducibility.

Create (sync — quick test only)

curl -X POST 'https://api.pruna.ai/v1/predictions' \
  -H 'Content-Type: application/json' \
  -H "apikey: ${PRUNA_API_KEY}" \
  -H 'Model: p-image' \
  -H 'Try-Sync: true' \
  -d '{"input":{"prompt":"Corgi cowboy lassoing a runaway taco truck through Monument Valley dust storm, pulp western poster energy, dynamic diagonal composition","aspect_ratio":"16:9"}}'

Generation flow

Follow generation-diversity still-image prompt flow every time:

1. Lock brief — user subject, product, format, any copy-on-surface.
2. Ritual seed — fresh string; derive free axes (camera, lighting, render_category_tag, aspect_ratio when unset).
3. Draft explicit prompt — Prompt craft (dynamic + faithful) + image-prompting golden rules; fidelity check before pay.
4. Confirm — show prompt + aspect_ratio unless wording is locked.
5. POST — async curl below; poll via pruna-api; run p-image quality checklist before upscale/video.

Aspect ratio: pass aspect_ratio in input; if output dimensions do not match (e.g. asked 16:9, got portrait), retry once with explicit horizontal wide / vertical wording in the prompt.

Mood board / batch: new ritual per independent still; different aspect_ratio per panel when format not locked.

Photo approved → edit: hand off to p-image-edit on the output URL — do not run photo generation again for the same subject.

Required input

• prompt (string)

Common optional fields

• aspect_ratio: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, custom (with width / height multiples of 16, 256–1440)
• seed, lora_weights, lora_scale, hf_api_token, disable_safety_checker

Typical next steps

Common follow-ons after this skill: