Skip to content

sae: add counterfactual image-edit evaluation #25

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
mgagvani wants to merge 5 commits into
base: sae/foundation
Choose a base branch
from
Open

sae: add counterfactual image-edit evaluation #25

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
0644654
sae: add counterfactual image-edit evaluation
mgagvani Jul 29, 2026
a163d04
Merge branch 'sae/foundation' into sae/counterfactual-edits
mgagvani Jul 30, 2026
f8b1d4b
sae: stream stage 1 edit generation instead of preloading
mgagvani Aug 5, 2026
62a9584
sae: do not report t / dz where variance is undefined
mgagvani Aug 5, 2026
00791e0
sae: resume stage 1 from an existing manifest
mgagvani Aug 5, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 14 additions & 0 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,3 +9,17 @@ dependencies = [
"ipython>=8.23.0",
"waymo-open-dataset-tf-2-12-0==1.6.7",
]

[project.optional-dependencies]
# Only needed by analyze_sae_visual_gen.py (stage 1 of the counterfactual
# image-edit pipeline): object detection, VLM prompt generation, and the
# diffusion image editor. Stage 2 (analyze_sae_visual_gen_pt2.py) and every
# other SAE script run without these.
visual-edits = [
"diffusers>=0.31",

@chatgpt-codex-connector chatgpt-codex-connector Bot Jul 29, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

P2 Badge Raise the minimum diffusers version

diffusers==0.31 satisfies this declared dependency but predates the QwenImageEditPipeline, QwenImageEditPlusPipeline, and Flux2KleinPipeline symbols imported unconditionally by stage 1. In an otherwise valid environment constrained to that allowed version, the script fails during import before any editor can be selected. Set the lower bound to the first release that exports all three pipelines, or import each optional pipeline lazily.

Useful? React with 👍 / 👎.

"google-genai>=0.3",
"openai>=1.0",
"pillow>=10.0",
"python-dotenv>=1.0",
"ultralytics>=8.3",
]
Loading