resize_token_embeddings (?) (different result from new and old version)

[Red-Owl]

System Info

model, and embending https://huggingface.co/fofr/sdxl-emoji

detail image: emoji_20250813_002621_2c661c36-1825-496f-84b4-60ec59a961fe.json

from requirements.txt

to:
new_requirements.txt

the code is: (not changed)
generation.txt

Who can help?

tokenizers: @ArthurZucker and @itazap
pipelines: @Rocketknight1

Information

• The official example scripts
• My own modified scripts

Tasks

• An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
• My own task or dataset (give details below)

Reproduction

code top

Expected behavior

view image

[Rocketknight1]

Hi @Red-Owl, this code is way too long and wrapped in a Flask app! Can you please simplify it and be clear about what the issue is? We get hundreds of issues per day and we don't have time to take apart your codebase, so we need the smallest reproducer possible if you want us to diagnose and fix a bug

[Red-Owl]

text2.py.txt change weight of lora , in new and old requirements.txt new transformers not load lora

[Rocketknight1]

Transferring to diffusers! cc @sayakpaul

[sayakpaul]

Please provide more details and a minimal reproduction.