IMG2.5 Surreal Hatchery Manual · skill pubblica Open Skill
IMG2.5 Surreal Hatchery Manual
IMG2.5 Surreal Hatchery Manual è una Open Skill pubblica su Digen. Aprila per vedere cosa crea questo workflow.
Custom
0 0 0
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/3325120/2026-10-14/p26sw6ps.jpg
# IMG2.5 Surreal Hatchery Manual Create one **hyper-realistic cinematic still**: an **open vintage hardcover book** whose **stacked pages become walls, floors, and catwalks** of a **miniature hatchery laboratory** carved inside the spread. **Cool blue neon** clinical light, **glowing glass specimen tubes** with **fictional non-human embryos**, a **partially concealed conveyor belt** threading through the paper architecture, and a **luminous Eye of Providence** emblem on the inner back wall. Optional **book cover photo** personalizes spine, palette, and title; the surreal lab interior stays on-brand. No structured project state. Progress is conversation + canvas asset. ## Global language lock Handbook (this file + all `references/`) is **English only — zero Han/CJK**. User-facing copy uses locked **`user_lang`** per `references/00-language.md`. Image `prompt` is **always English**. ## Pause + guidance (hard) **Every time you stop and wait for the user**, call **`set_guidance` in the same turn** as the last user-visible message — **no exceptions**. Pauses include: missing optional inputs when you choose to ask, policy refusal, explain-the-look without generate, recoverable failure, and **after every successful image**. Before any pause turn, `read_skill_file` → `references/guidance-buttons.md` and pick **2–4** actionable buttons for that situation. - **Forbidden:** ending a wait turn with only prose and no `set_guidance`. - On the `set_guidance` turn: **no other tools** in that turn. ## User-visible speech (hard) The user must not see the pipeline. Tools still run; chat text does not narrate them. **Never tell the user:** that you are reading a skill or reference; todos; tool names; channel names (`t2i`, `i2i.hd.gpt`, …); `SCENE LOCK`; the full prompt; `entity_type`; silent QC or redo. **Allowed user-visible text:** - Optional intake: one short question only when the user gave no book photo and no title/specimen hints — offer defaults via buttons. **Stop** with `set_guidance`. - Starting: at most one short line in **`user_lang`**. Then tools only until the image is ready (no pause mid-pipeline except failures that require user choice). - Success: one or two sentences in **`user_lang`**. Same turn: **`set_guidance` only** (no other tools). - `success=false` when user action can help: short failure note + **`set_guidance`** in the same turn. - Refuse: short polite refusal + **`set_guidance`**. If the user already asked to generate (with or without a book photo), **do not** run a long questionnaire — read the template and generate with sensible defaults. ## When to use - User wants a **surreal book diorama**: vintage open book → **miniature hatchery lab** built from **pages**. - User mentions **specimen tubes**, **conveyor belt**, **watchful eye / Eye of Providence**, **blue neon clinical** mood. - User uploaded a **book cover or spine photo** to personalize the outer book while keeping the inner lab concept. - Follow-up: change **fictional book title**, **specimen creature design**, **more/less neon**, **landscape vs portrait**, or **regenerate** from last result. Do **not** use for: ordinary flat book illustration, typography-only layouts, real-world biolab photography without the book metaphor, **video**, or **real human fetal / gore** content. ## Reference files | File | When | |---|---| | `references/scene-template.md` | Assemble prompt, redo, or user asks what the look is | | `references/guidance-buttons.md` | Any pause turn (before `set_guidance`) | | `references/00-language.md` | First user-visible message; before `set_guidance` | Do not tell the user you are reading these files. ## Channel Every `generate_image` must pass `model`. No physical model names. Never bare `i2i`. | Mode | When | `input_urls` | `model` | |---|---|---|---| | **i2i** | User uploaded a book/cover/spine photo to personalize the outer book | required (that image, or last result if editing) | default **`i2i.hd.gpt`**; user asks li