Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix long prompt weighting bug in ckpt codepath

Browse Source
This commit is contained in:
Damian Stewart 2023-01-21 12:06:23 +01:00
parent b3363a934d
commit e94c8fa285
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
ldm/modules/encoders/modules.py
View File

@ -654,14 +654,15 @@ class WeightedFrozenCLIPEmbedder(FrozenCLIPEmbedder):
per_token_weights += [weight] * len(this_fragment_token_ids)
# leave room for bos/eos
if len(all_token_ids) > self.max_length - 2:
excess_token_count = len(all_token_ids) - self.max_length - 2
max_token_count_without_bos_eos_markers = self.max_length - 2
if len(all_token_ids) > max_token_count_without_bos_eos_markers:
excess_token_count = len(all_token_ids) - max_token_count_without_bos_eos_markers
# TODO build nice description string of how the truncation was applied
# this should be done by calling self.tokenizer.convert_ids_to_tokens() then passing the result to
# self.tokenizer.convert_tokens_to_string() for the token_ids on each side of the truncation limit.
print(f">> Prompt is {excess_token_count} token(s) too long and has been truncated")
all_token_ids = all_token_ids[0:self.max_length]
per_token_weights = per_token_weights[0:self.max_length]
all_token_ids = all_token_ids[0:max_token_count_without_bos_eos_markers]
per_token_weights = per_token_weights[0:max_token_count_without_bos_eos_markers]
# pad out to a 77-entry array: [eos_token, <prompt tokens>, eos_token, ..., eos_token]
# (77 = self.max_length)