Skip to content

Added WD14 Auto Caption task#15

Open
ParamThakkar123 wants to merge 6 commits into
mainfrom
add/auto-caption
Open

Added WD14 Auto Caption task#15
ParamThakkar123 wants to merge 6 commits into
mainfrom
add/auto-caption

Conversation

@ParamThakkar123
Copy link
Copy Markdown
Contributor

No description provided.

@ParamThakkar123 ParamThakkar123 changed the title Added WD14 Autocaption task Added WD14 Auto Caption task Feb 2, 2026
Comment thread auto-caption-wd14/main.py Outdated
Copy link
Copy Markdown
Member

@deep1401 deep1401 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You will need to convert the task.json to task.yaml now, please refer here: https://lab.cloud/for-teams/task-yaml/task-structure

Comment thread auto-caption-wd14/task.yaml Outdated
name: auto-caption-wd14
resources:
accelerators: "RTX3090:1"
setup: "uv pip install transformerlab torchvision huggingface-hub"
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You're importing datasets but dont install it. Maybe also look at installing the correct version of transformers

Comment thread auto-caption-wd14/main.py
import tempfile
from datetime import datetime
from PIL import Image, ImageDraw, ImageFont, ImageFilter
import tensorflow as tf
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do we need tensorflow somewhere?
If not then maybe we shouldn't import it?
I started a task and it failed because tensorflow was not installed and then when I added tensorflow to the uv pip install setup stuff and ran another job, I got the following error:

WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1776442839.004594    9195 cpu_feature_guard.cc:227] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
Traceback (most recent call last):
  File "/home/sky/auto-caption-wd14/main.py", line 23, in <module>
    from huggingface_hub import from_pretrained_keras, hf_hub_download
ImportError: cannot import name 'from_pretrained_keras' from 'huggingface_hub' (/home/sky/miniconda3/lib/python3.10/site-packages/huggingface_hub/__init__.py)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants