From 8e2aeee4a127b295bfc880800e4a312e0f049b85 Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Sun, 15 Jan 2023 22:29:53 +0300
Subject: add BREAK keyword to end current text chunk and start the next

---
 modules/prompt_parser.py  |  7 ++++++-
 modules/sd_hijack_clip.py | 17 +++++++++++++----
 2 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/modules/prompt_parser.py b/modules/prompt_parser.py
index 870218db..69665372 100644
--- a/modules/prompt_parser.py
+++ b/modules/prompt_parser.py
@@ -274,6 +274,7 @@ re_attention = re.compile(r"""
 :
 """, re.X)
 
+re_break = re.compile(r"\s*\bBREAK\b\s*", re.S)
 
 def parse_prompt_attention(text):
     """
@@ -339,7 +340,11 @@ def parse_prompt_attention(text):
         elif text == ']' and len(square_brackets) > 0:
             multiply_range(square_brackets.pop(), square_bracket_multiplier)
         else:
-            res.append([text, 1.0])
+            parts = re.split(re_break, text)
+            for i, part in enumerate(parts):
+                if i > 0:
+                    res.append(["BREAK", -1])
+                res.append([part, 1.0])
 
     for pos in round_brackets:
         multiply_range(pos, round_bracket_multiplier)
diff --git a/modules/sd_hijack_clip.py b/modules/sd_hijack_clip.py
index 852afc66..9fa5c5c5 100644
--- a/modules/sd_hijack_clip.py
+++ b/modules/sd_hijack_clip.py
@@ -96,13 +96,18 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module):
         token_count = 0
         last_comma = -1
 
-        def next_chunk():
-            """puts current chunk into the list of results and produces the next one - empty"""
+        def next_chunk(is_last=False):
+            """puts current chunk into the list of results and produces the next one - empty;
+            if is_last is true, tokens <end-of-text> tokens at the end won't add to token_count"""
             nonlocal token_count
             nonlocal last_comma
             nonlocal chunk
 
-            token_count += len(chunk.tokens)
+            if is_last:
+                token_count += len(chunk.tokens)
+            else:
+                token_count += self.chunk_length
+
             to_add = self.chunk_length - len(chunk.tokens)
             if to_add > 0:
                 chunk.tokens += [self.id_end] * to_add
@@ -116,6 +121,10 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module):
             chunk = PromptChunk()
 
         for tokens, (text, weight) in zip(tokenized, parsed):
+            if text == 'BREAK' and weight == -1:
+                next_chunk()
+                continue
+
             position = 0
             while position < len(tokens):
                 token = tokens[position]
@@ -159,7 +168,7 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module):
                 position += embedding_length_in_tokens
 
         if len(chunk.tokens) > 0 or len(chunks) == 0:
-            next_chunk()
+            next_chunk(is_last=True)
 
         return chunks, token_count
 
-- 
cgit v1.2.1