Anime to Realistic · مهارة Open Skill عامة
Anime to Realistic
Anime to Realistic هي Open Skill عامة على Digen. افتحها لتعرف ماذا ينشئ هذا التدفق.
Custom
7 0 2
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4173183/2026-10-15/2efq4z9s.jpg
# Anime to Realistic Turn **anime-style illustration input** into **one photorealistic photograph of the same scene**: real-world photographic rendering, lifelike skin and material texture, natural lighting and shadows, physically accurate depth of field, fine surface detail, high-fidelity realism while **preserving the original composition and subject**. Supports **upload (I2I)**, **direct generate with no upload** (internal anime still then conversion—user sees the photoreal result), **text-only scene brief**, and **refine last photoreal output**. No project state. **Language lock:** This file and all of `references/` are **English only** (no Han / CJK characters). Reply in the **user's language**. Every `generate_image` `prompt` is **English**. Do not tell the user tool names, channel names, or full generation prompts unless they explicitly ask to see the prompt. ## User-visible speech (hard) Do not narrate the two-step direct-generate pipeline. Never mention skill files, `read_skill_file`, hidden intermediates, silent redo, or channels. **Allowed lines only:** - Need input: one short note that they may **tap direct generate**, **describe a scene**, or **upload anime art** — 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 **photorealistic version of the scene** 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. Localize `text` and `content` to the user's language. No channel or tool names on buttons. Before every pause turn, `read_skill_file` → `references/guidance-buttons.md`. | Pause | When | Example intents (localize) | |---|---|---| | P-empty | No upload, no usable brief, no direct-generate tap, no last photoreal to refine | Direct generate now · Describe my scene · I'll upload anime art | | P-brief | Text too vague (no subject or setting) | Example scene brief (`fill_input`) · Direct generate default (`send_message`) | | P-refuse | NSFW goal, sexualized minor, hate target, gore-as-subject | Family-safe direct generate · Upload different art | | P-fail | `generate_image` `success=false` after retry | Direct generate again · Regenerate from same upload · Upload a different image | | P-done | One photoreal scene ready | Stronger realism · Softer natural light · Direct generate new scene · Refine last result | ## When to use - User uploads **anime or manga-style color illustration** and wants a **real-photo look** of the **same scene**. - User has **no image** or taps **direct generate** / **generate without upload** — run the **direct-generate pipeline** in `references/generation.md` (anime still hidden, photoreal shown) unless the same message already describes a different scene. - User gives a **text scene brief** without upload — if subject + setting are clear, run direct-generate pipeline or single-shot path per `references/generation.md`. - User asks to **retry**, **push realism**, **adjust lighting**, **fix hands/face**, or **change framing** on the **last successful photoreal** from this skill. **Do not use:** plain anime generation only (no photoreal goal); inverse real-photo →