Claude
6fcd3b8a86
Rebase the DSL text encoder on comfy.sd1_clip.SDClipModel and comfy.clip_model.CLIPTextModel_, replacing the old HuggingFace transformers CLIPTextModel/CLIPTextTransformer/CLIPTextEmbeddings subclasses (which are no longer how ComfyUI implements CLIP). Structure: - Merge lib/action/ into lib/actions/; drop lib/fun_clip_stuff.py and the bundled clip_config*.json (comfy ships its own) - Convert all custom_nodes.KepPromptLang.* absolute imports to relative imports so installs via Manager work regardless of install directory name Encoder: - PromptLangSDClipModel overrides encode_token_weights to walk the segment/action tree, assemble [B, seq, hidden] embeds, and call self.transformer(None, mask, embeds=..., num_tokens=...) - posScale / postPos are supported without patching the transformer by pre-baking the delta (modified - default) into embeds, so the transformer's inline add yields the modified position embedding - Drop the unused empty-baseline batch that was prepended and then sliced off; halves the per-encode forward pass for single prompts Actions: - Fix copy-pasted broken __repr__ / depth_repr across sum/diff/avg/ slerp that referenced fields that didn't exist - Fix NameError in AverageAction._validate_args (start_arg_token_length) - Fix class-level mutable state in RandAction - Unify _parse_scalar / _parse_scalar_weight / _parse_int into a single parse_numeric_arg helper in action_utils.py - Share add_with_broadcast between SumAction and DiffAction - Convert PostModifiers from TypedDict to dataclass (attribute access catches typos that .get() on string keys hides) Drop the two _exp-pooler / _exp-pooledAvg actions: they recursively invoked the HF CLIPTextTransformer and would need a rework to fit the current CLIPTextModel_ interface. They were experimental and not documented as stable. BuildGif node: - Collapse the 10-positional-arg _save_* helpers onto a small _SaveContext dataclass - Stop mutating the input arg semantics (split_every_val was reassigned to len(images) when -1) Tests: - Add pytest suite covering the parser (grammar, nesting, errors) and every action (embedding math, shape, modifier payloads) - conftest stubs ComfyUI at collection time so tests don't need a real ComfyUI install Drop the broken test_files/ scripts (CI helpers, not a test suite) and regenerate the README from tools/build_docs.py.
40 lines
1.2 KiB
Python
40 lines
1.2 KiB
Python
from typing import List
|
|
|
|
from torch import Tensor
|
|
from torch.nn import Embedding
|
|
|
|
from .action_utils import add_with_broadcast, concat_embeddings
|
|
from .base import MultiArgAction
|
|
from .types import SegOrAction
|
|
|
|
|
|
class DiffAction(MultiArgAction):
|
|
grammar = 'diff(" arg ("|" arg)* ")"'
|
|
|
|
display_name = "Difference"
|
|
action_name = "diff"
|
|
description = (
|
|
"Subtracts the segments in the order they are given. "
|
|
"The first segment is subtracted from the second, then the third from the result, and so on."
|
|
)
|
|
usage_examples = [
|
|
"diff(The cat is|The dog is)",
|
|
"diff(Cat|Dog)",
|
|
"sum(diff(king|man)|woman)",
|
|
]
|
|
|
|
def __init__(self, args: List[List[SegOrAction]]) -> None:
|
|
super().__init__(args)
|
|
self.base_arg = args[0]
|
|
self.additional_args = args[1:]
|
|
|
|
def token_length(self) -> int:
|
|
return sum(s.token_length() for s in self.base_arg)
|
|
|
|
def get_result(self, embedding_module: Embedding) -> Tensor:
|
|
result = concat_embeddings(self.base_arg, embedding_module)
|
|
for arg in self.additional_args:
|
|
arg_embedding = concat_embeddings(arg, embedding_module)
|
|
result = add_with_broadcast(result, arg_embedding, op="sub")
|
|
return result
|