新方案v1角色结构理解

prompts/complete-v1.txt

@@ -0,0 +1,10 @@
+Complete only the hidden portion of the specified character part on the first
+input image (the local canvas). Any subsequent images are context references.
+Preserve the exact original pose, scale, screen direction, perspective, colors,
+line thickness and shading. Do not mirror, rotate, resize, recenter or redesign.
+Keep the canvas dimensions and the position of every already-visible feature.
+Extend the hidden joint area naturally behind its occluder, without adding other
+body parts, props, labels, annotations or extra versions of the same part.
+If an edit mask is supplied, transparent mask pixels are editable. If no edit
+mask is supplied, this request is only an adapter experiment, not a guaranteed
+pixel-preserving final asset. A later stage will restore source visible pixels.

prompts/understand-v1.txt

@@ -0,0 +1,20 @@
+Analyze the supplied single character image for a Spine cutout animation pipeline.
+Return a JSON part plan, not an image. Preserve the exact pose, asymmetry, clothing,
+and screen-left/screen-right orientation. Do not require a fixed number of parts.
+Use stable lowercase ASCII IDs (letters, numbers, underscores, hyphens).
+Separate parts only where independent motion is useful and the image supports it.
+Parent refers to the motion hierarchy; null means attached to the future root bone.
+Occlusion is a separate relation: occluded_by lists parts visually in front.
+All coordinates are normalized to the full supplied canvas, including transparent
+margins. bbox_norm_xyxy is [xmin,ymin,xmax,ymax], never [x,y,width,height].
+pivot_norm is the estimated attachment joint, not necessarily the bbox center.
+For visible or partly visible parts give a coarse visible bbox and positive points
+inside visible pixels; optional negative points identify nearby other parts.
+Do not claim precise pixel masks. A segmentation stage will refine boundaries.
+If a part is fully hidden, mark visibility="hidden", bbox_norm_xyxy=null,
+positive_points_norm=[], needs_completion=true and explain the uncertainty.
+Do not invent hidden limbs or accessories without visual evidence. Put assumptions
+in notes. Confidence is your uncertainty estimate, not a measured segmentation score.
+Avoid cycles in parent and occluded_by relations. If an object crosses in front
+and behind another, split its visual layers or flag the ambiguity in notes.
+Return schema_version=1, coordinate_space="normalized_xy_top_left", parts, notes.