sn-image-imitate

1# sn-image-imitate
2 
3Image style imitation scene skill (tier 1), relying on the `sn-image-recognize`, `sn-text-optimize`, and `sn-image-generate` tools provided by `sn-image-base` (tier 0).
4 
5Features:
6 
7- Extracts high-fidelity long caption from a reference image
8- Rewrites caption according to user requested content change while preserving style and layout
9- Enforces layout-lock constraints during caption rewrite
10- Performs post-generation layout consistency review and bounded retries
11- Returns structured process artifacts for debugging and reproducibility
12 
13## Non-goals
14 
15- Pure neural style transfer without content change (use dedicated style-transfer tools instead)
16- Local editing / inpainting of specific regions within the reference image
17- Processing video or animation input (only single static images are supported)
18- Batch generation from multiple reference images in one invocation
19- Guaranteeing pixel-level fidelity to the reference; the skill targets layout and style consistency, not exact reproduction
20 
21## Input Specification
22 
23- `reference_image` (string, required): local path or URL of the style reference image
24- `target_content` (string, required): new content user wants in the generated image
25- `output_mode` (string, default `friendly`): output mode, `friendly` or `verbose`
26- `aspect_ratio` (string, default `16:9`): output aspect ratio for generation
27- `image_size` (string, default `2k`): output image size preset
28…