DemonGatanjieuandClaude Opus 5.5
414e76c935
- header_words.py: modelspec.trigger_phrase, else the tags most training pictures share (ss_tag_frequency, generic ones left out); the scanner keeps them as anomalous_header_words when Civitai gives no trigger words, metadata gives headerWords, model search finds them. - model_kind: Flux Schnell told from Dev (no guidance_in), Z-Image from Lumina 2 (caption embedder width, a GGUF by parameter count); RULES 3 so kept header answers are read again. - api/model_guide.py + model_profiles.json: GET /anomalous/model_guide for the model details (example settings, header words, the text encoder and VAE a diffusion models file needs, found by name), and get_model's header_words and usage for the AI. - model_advice.example_settings gives the author's example settings as values; author_examples says them in words as before. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
66 lines
3.4 KiB
Python
66 lines
3.4 KiB
Python
"""What a LoRA's own header suggests for the prompt when Civitai gives no trigger words
|
|
(header_words.py): the maker's trigger phrase, else the tags most training pictures share."""
|
|
import json
|
|
import os
|
|
import struct
|
|
import sys
|
|
import tempfile
|
|
import unittest
|
|
from pathlib import Path
|
|
|
|
PLUGIN = Path(__file__).resolve().parents[1]
|
|
sys.path[:0] = [str(PLUGIN), str(PLUGIN.parents[1])]
|
|
|
|
import header_words # noqa: E402
|
|
|
|
LORA_KEY = "lora_unet_input_blocks_4_1_proj_in.lora_down.weight"
|
|
|
|
|
|
def model_file(folder, name, keys, meta):
|
|
header = {key: {"dtype": "F16", "shape": [4, 4], "data_offsets": [0, 0]} for key in keys}
|
|
header["__metadata__"] = meta
|
|
raw = json.dumps(header).encode("utf-8")
|
|
path = os.path.join(folder, name)
|
|
Path(path).write_bytes(struct.pack("<Q", len(raw)) + raw + b"\0" * 8)
|
|
return path
|
|
|
|
|
|
class WordTests(unittest.TestCase):
|
|
def test_the_makers_phrase_comes_first(self):
|
|
meta = {"modelspec.trigger_phrase": " glowstyle, neon rim ,", "ss_tag_frequency": json.dumps({"d": {"other": 5}})}
|
|
self.assertEqual(header_words.from_meta(meta), ["glowstyle", "neon rim"])
|
|
|
|
def test_tags_most_training_pictures_share_without_the_generic_ones(self):
|
|
tags = {"10_mychar": {"mychar": 40, "1girl": 40, "solo": 39, "blue eyes": 36, "looking_at_viewer": 30,
|
|
"red scarf": 26, "smile": 25, "hat": 5, "score_9": 40},
|
|
"2_extra": {"mychar": 10, "blue eyes": 9}}
|
|
self.assertEqual(header_words.from_meta({"ss_tag_frequency": json.dumps(tags)}), ["mychar", "blue eyes", "red scarf"],
|
|
"in half as many pictures as the most used tag at least, most used first")
|
|
|
|
def test_at_most_five_and_nothing_from_broken_metadata(self):
|
|
many = {"d": {f"tag{number}": 10 for number in range(9)}}
|
|
self.assertEqual(len(header_words.from_meta({"ss_tag_frequency": json.dumps(many)})), 5)
|
|
self.assertEqual(header_words.from_meta({"ss_tag_frequency": "{not json"}), [])
|
|
self.assertEqual(header_words.from_meta({"ss_tag_frequency": json.dumps({"d": {"x": "many", "y": True}})}), [])
|
|
self.assertEqual(header_words.from_meta({"ss_tag_frequency": json.dumps(["a", "b"])}), [])
|
|
self.assertEqual(header_words.from_meta({}), [])
|
|
|
|
def test_only_lora_files_are_read(self):
|
|
with tempfile.TemporaryDirectory() as temp:
|
|
tags = {"ss_tag_frequency": json.dumps({"d": {"mychar": 3}})}
|
|
self.assertEqual(header_words.of_file(model_file(temp, "l.safetensors", [LORA_KEY], tags)), ["mychar"])
|
|
checkpoint = model_file(temp, "c.safetensors", ["model.diffusion_model.input_blocks.0.0.weight",
|
|
"first_stage_model.decoder.up.0.block.0.conv1.weight"], tags)
|
|
self.assertEqual(header_words.of_file(checkpoint), [], "a fine-tune's training tags are no trigger words")
|
|
pickle = os.path.join(temp, "x.ckpt")
|
|
Path(pickle).write_bytes(b"\x80\x02whatever")
|
|
self.assertEqual(header_words.of_file(pickle), [], "formats that can carry code are never opened")
|
|
broken = os.path.join(temp, "b.safetensors")
|
|
Path(broken).write_bytes(struct.pack("<Q", 10 ** 12))
|
|
self.assertEqual(header_words.of_file(broken), [])
|
|
self.assertEqual(header_words.of_file(os.path.join(temp, "missing.safetensors")), [])
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|