DemonGatanjieuandClaude Opus 5.5
f7d8a69e75
The descriptions of the daily set are rewritten without the repeats and roundabout phrasing. Their rules and don'ts stay: no cropping or editing pictures with code, no reading ComfyUI's folders, ask the user in the workbench. So do the shared property texts: the query words, node ids, the task id. tools/list for the daily set drops from about 27,300 to 22,200 characters, and the full one from 46,000 to 40,700. begin_task's note, read at the start of every task, drops from about 1,900 to 900 characters. The replacements were made with ast, so each description's adjacent literals changed as one. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
87 lines
4.6 KiB
Python
87 lines
4.6 KiB
Python
"""zoom_image, the AI's closer look: part of a picture (in ComfyUI's output, input or temp folder)
|
|
cut out and shown larger, and the same part of a second picture beside it to compare a before
|
|
and an after, attached to the answer. It reads only: the pictures stay as they are. With it an AI
|
|
need not crop, enlarge or compare pictures with code of its own (each such command asks the user
|
|
to allow it). The region is in fractions of the picture, as the user's marks give theirs."""
|
|
|
|
import base64
|
|
import io
|
|
|
|
from PIL import Image
|
|
|
|
from .mcp_tools import ToolError, _resolve_folder_image, _tool
|
|
|
|
MIN_SIZE, MAX_SIZE, DEFAULT_SIZE = 256, 1024, 768
|
|
MAX_ENLARGE = 4 # a tiny part is shown at most this many times its size
|
|
MIN_PIXELS = 8
|
|
|
|
|
|
def _box(region, width, height):
|
|
"""Region {x, y, width, height} (fractions 0-1, default the whole picture) as a pixel box."""
|
|
region = region if isinstance(region, dict) else {}
|
|
try:
|
|
x, y = (min(1.0, max(0.0, float(region.get(key, 0)))) for key in ("x", "y"))
|
|
w, h = (min(1.0, max(0.0, float(region.get(key, 1)))) for key in ("width", "height"))
|
|
except (TypeError, ValueError):
|
|
raise ToolError("region is {x, y, width, height}, each a fraction 0-1 of the picture.")
|
|
left, top = round(x * width), round(y * height)
|
|
right, bottom = min(width, round((x + w) * width)), min(height, round((y + h) * height))
|
|
if right - left < MIN_PIXELS or bottom - top < MIN_PIXELS:
|
|
raise ToolError(f"The region is under {MIN_PIXELS} pixels across; give a larger one.")
|
|
return left, top, right, bottom
|
|
|
|
|
|
def _part(path, region, size):
|
|
"""(facts, MCP image item) of `region` of the picture at `path`, its longer side `size` at most."""
|
|
try:
|
|
with Image.open(path) as picture:
|
|
box = _box(region, picture.width, picture.height)
|
|
part = picture.crop(box).convert("RGB")
|
|
whole = f"{picture.width}x{picture.height}"
|
|
except (OSError, ValueError, Image.DecompressionBombError):
|
|
raise ToolError("The picture cannot be read.")
|
|
scale = min(size / max(part.size), MAX_ENLARGE)
|
|
shown = part.resize((max(1, round(part.width * scale)), max(1, round(part.height * scale))), Image.LANCZOS)
|
|
data = io.BytesIO()
|
|
shown.save(data, "JPEG", quality=88)
|
|
facts = {"picture": whole, "region": f"x {box[0]}-{box[2]}, y {box[1]}-{box[3]} px", "shown": f"{shown.width}x{shown.height}"}
|
|
return facts, {"type": "image", "data": base64.b64encode(data.getvalue()).decode("ascii"), "mimeType": "image/jpeg"}
|
|
|
|
|
|
def zoom_image(image, region=None, folder="output", compare_with="", compare_folder="", size=DEFAULT_SIZE):
|
|
try:
|
|
size = min(MAX_SIZE, max(MIN_SIZE, int(size)))
|
|
except (TypeError, ValueError):
|
|
raise ToolError(f"size is {MIN_SIZE}-{MAX_SIZE} pixels.")
|
|
rel, path = _resolve_folder_image(image, folder)
|
|
facts, item = _part(path, region, size)
|
|
answer = {"image": rel, "folder": folder, **facts}
|
|
extra = [item]
|
|
if compare_with:
|
|
other_folder = compare_folder or folder
|
|
other_rel, other_path = _resolve_folder_image(compare_with, other_folder)
|
|
other_facts, other_item = _part(other_path, region, size)
|
|
answer["compare_with"] = {"image": other_rel, "folder": other_folder, **other_facts}
|
|
answer["note"] = "Two pictures are attached: first image, then compare_with, the same region of each."
|
|
extra.append(other_item)
|
|
return answer, extra
|
|
|
|
|
|
_REGION = {"type": "object", "description": "Fractions 0-1, like the user's marks; default all.",
|
|
"properties": {name: {"type": "number", "minimum": 0, "maximum": 1} for name in ("x", "y", "width", "height")}}
|
|
_FOLDER = {"type": "string", "enum": ["output", "input", "temp"], "default": "output"}
|
|
|
|
LOOK_TOOLS = dict([
|
|
_tool("zoom_image", "Look closer at a picture",
|
|
"Part of a picture larger, at full detail (a hand, a face, a seam). folder: output, input or temp. "
|
|
"compare_with: a second picture, the same region beside it. Use it instead of cropping with code; "
|
|
"change pictures only by running a workflow, never by editing their files.",
|
|
zoom_image, {"image": {"type": "string", "description": "As the other tools name it."},
|
|
"region": _REGION, "folder": _FOLDER,
|
|
"compare_with": {"type": "string", "description": "A second picture."},
|
|
"compare_folder": {"type": "string", "enum": ["output", "input", "temp"],
|
|
"description": "Default: folder."},
|
|
"size": {"type": "integer", "minimum": MIN_SIZE, "maximum": MAX_SIZE, "default": DEFAULT_SIZE}},
|
|
["image"]),
|
|
])
|