/xxg-portrait-rebuild-light

name: xxg-portrait-rebuild-light
description: "Edit an existing JPG, JPEG, PNG, or WebP portrait to rebuild physically coherent light, exposure, color, capture style, clean optical skin, and frame quality without changing the person. Use for plastic-skin or AI-look removal, dirty synthetic texture, banding, edit seams, color drift, multi-round quality loss, tone or white-balance correction, camera/film/device emulation, backlight, prism, blind shadows, candlelight, neon, golden hour, rim light, rain-wet low key, studio light, or silhouettes."

XXG Portrait Rebuild Light V2.3

Objective

Treat the input as the same photograph, never as a reference for a replacement portrait. Improve illumination, exposure, color rendering, capture character, skin response, and generation quality while retaining identity, facial geometry and natural asymmetry, expression, pose, camera view, framing, and subject scale. Preserve source optics unless the user explicitly requests an optical restyle.

Build realism from three separable signals:

1. clean low-frequency skin tone and broad transitions; 2. source-driven diffuse/specular response with highlights confined to plausible light-facing areas; 3. fine, region-specific microdetail limited by face scale, focus, and illumination.

Do not manufacture realism with dirt, darkness, coarse pores, uniform grain, random color patches, or exaggerated facial lines. The result must first read as a clean photograph at normal size.

Choose the Edit Scope

• **`texture-only`**: when the user asks only to remove plastic/AI skin or recover detail, force `L0 + E0 + T0 + G0 + D0 + A0 + Q0`. Preserve the source lighting, highlight placement, exposure, white balance, focal plane, depth of field, and background.
• **`tone-and-exposure`**: when the user asks for brightness, highlight/shadow recovery, white balance, palette, or grading without new lighting, preserve the source light direction and edit only E/T/G.
• **`relight-and-skin`**: when the user requests a lighting change or selects L/T/A, authorize the requested light response while preserving source focal plane and depth of field unless explicitly changed.
• **`capture-style`**: when the user requests a camera, film, phone, CCD, or era look, edit G/D and only the exposure behavior logically required by that capture; preserve viewpoint, crop, focal plane, and depth of field.
• **`optical-restyle`**: only when the user explicitly requests a different focal-length perspective, camera angle, aperture behavior, or depth of field. State that axis once and permit only the minimum framing/background reconstruction it requires.
• **`quality-repair`**: when the user asks to remove dirty synthetic patterns, banding, posterization, seams, halos, or other generation residue, edit only Q and preserve light, color, structure, optics, and natural texture.
• **`base-color-repair`**: when an edited result has an unintended cast, use the original root base to restore only unchanged or unauthorized color relationships; preserve deliberate recolors and requested E/T/G/A changes.
• **`multi-round-repair`**: when repeated edits accumulate tint, noise, sharpening, compression, banding, or seams, use the latest accepted edit as the target and the first root base as the stable identity/geometry/color reference.

Never let texture repair become relighting, tone correction become a new light source, device emulation become a new pose/viewpoint, or quality cleanup become global smoothing or an unauthorized regrade.

Use the Host Image Editor

1. Inspect the source and read the host's native image-generation or image-editing skill. 2. Discover the actual callable in the tool registry. In Codex, inspect `ALL_TOOLS` and prefer the exact discovered name `image_gen__imagegen`. 3. For a local source in Codex, use the discovered tool and its real arguments:

const result = await tools.image_gen__imagegen({
  referenced_image_paths: ["/absolute/path/source.png"],
  prompt: "compact English image-edit prompt"
});
generatedImage(result);

Never guess `tools.image_gen` or `input_image`. Correct wrong members, arguments, or `TypeError` from the registered signature and retry. In Claude, OpenClaw, or another host, use the equivalent native image-edit action explicitly exposed by that host.

For base-anchored or multi-round repair, pass exactly `[CURRENT_EDIT, ROOT_BASE]` and state: Image 1 is the edit target; Image 2 is the original root reference for declared locked axes only. Do not attach every intermediate round.

Route the Outcome

| Observed state | Required action | | --- | --- | | Compatible image tool discovered | Invoke it. A small face, dense text, complex props, or edge contact lowers detail ambition but never blocks generation. | | Correct image tool returns a real error | Report the actual error, enter `prompt-only`, and return a complete compact prompt. | | Discovery completes with no compatible callable | Enter `invocation-handoff` and return a complete compact prompt. | | Result is nearly unchanged, changes identity, creates artificial skin, or misses the light | State that the result did not achieve the requested improvement, enter `prompt-handoff`, and recompile from the source. |

Reading a skill, inspecting an image, creating a task, or announcing generation is not an image-tool invocation.

Never Produce the Final Image Locally

Do not use Pillow, NumPy, OpenCV, ImageMagick, FFmpeg, `sips`, or custom raster scripts to relight, grade, retouch, sharpen, add texture, resize, crop, extend, composite, repair, or produce the delivered image. Use them only for read-only aspect-ratio, mask, and result audits. See `requirements.txt`.

Compile the Image Prompt

Read [the V2.3 prompt compiler](references/prompt-recipes.md), [the lighting and skin recipes](references/lighting-skin-color-temperature-recipes.md), [the tone/exposure/style/device recipes](references/tone-exposure-style-device-recipes.md), and [the qual