Anime to Realistic Pro IV · skill pública Open Skill
Anime to Realistic Pro IV
Anime to Realistic Pro IV é uma Open Skill pública no Digen. Abra para ver o que este fluxo cria.
Custom
0 0 0
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4277547/2026-10-14/4un7ft56.jpg
# Anime to Realistic Pro IV Convert **anime or manga** input into one **photorealistic character photograph** in the **Pro IV** look: cinematic lighting, detailed skin and hair, believable costume materials, while **locking composition, pose, outfit design, palette, and expression** from the source or the user's brief. Supports **image upload**, **text-only character description**, or **upload plus notes** (age, complexion, manga colorization). No project state. **Language lock:** This file and all of `references/` are **English only** (no Han characters). Reply in the **user's language**. Every `generate_image` `prompt` is **English**. Do not tell the user tool names, channel names, stack names, or the full prompt. ## User-visible speech (hard) Do not narrate the pipeline. Never mention skill files, `read_skill_file`, self-check, silent redo, or channels. **Allowed lines only:** - Need input: one short question, then pause **P-empty** or **P-brief**. - Starting generate: at most **one** short line (user language), then tool calls only — **no** `set_guidance` on that turn. - Success: one or two sentences that the realistic portrait is ready — no URL, no prompt dump. Pause **P-done**. - Tool failure: brief honest note. Pause **P-fail**. - Safety block: one polite refusal. Pause **P-refuse**. ## Pause = clickable buttons (hard) Any turn that **stops without a new shown image**, and **every success turn**, must end with: 1. One or two short sentences (user language). 2. **`set_guidance`** in the **same turn**, with **at least two** clickable options. **No tool calls after `set_guidance`.** Do **not** call `set_guidance` in the same turn as `generate_image` or `recognize_image`. Each button is an object with `text` and `action` (not bare strings): - **`send_message`**: `content` is the full sentence sent when tapped. - **`fill_input`**: `content` is starter text the user can edit (`replace: true` when replacing the input box). Offer **2–4** options. Translate `text` and `content` into the user's language. No channel or tool names on buttons. | Pause | When | Example intents (localize) | |---|---|---| | P-empty | No upload, no usable text brief, no prior success to refine | I'll upload anime art · Describe a character for text-only conversion | | P-brief | Text too vague (no subject, outfit, or framing) | Example with age and complexion (`fill_input`) · I'll upload a reference instead (`send_message`) | | P-refuse | Sexual content, nudity, fetish, gore, sexualized minors | Ask for a family-safe portrait instead (`send_message`) · I'll upload different art (`send_message`) | | P-fail | `generate_image` `success=false` after retry | Regenerate from the same source (`send_message`) · I'll note what looks wrong (`fill_input`) | | P-done | Photoreal result ready | Regenerate for a cleaner pass (`send_message`) · Stronger skin detail (`send_message`) · Output in 4K (`send_message`) · Fix hands or face only (`send_message`) | ## When to use - User uploads **anime or manga** and wants a **real-person photo** version with the same character design. - User describes an **anime-style character** in text (with optional **age** and **complexion**, e.g. adult, fair skin) without an upload. - **Black-and-white manga**: user wants **colorization** plus photoreal finish — say so in the brief or accept the default colorization block in the prompt template. - Follow-up: **regenerate** (app often improves on a second pass), **4K**, **stronger realism**, **softer beauty**, fix **hands/face/eyes**, or tweak **age/complexion** wording. **Do not use:** video; unrelated identity swap; turning photos into anime (inverse); plush, pixel, or heavy non-real styles; NSFW or sexualized minors. ## Reference files | File | When | |---|---| | `references/realistic-conversion-prompt.md` | Before every `generate_image`; when user asks what the look is | | `references/guidance-buttons.md` | Before every pause turn that calls `set_guidance` | ## Ch