#
alignprop
Here are 2 public repositories matching this topic...
Promptable, training-free, plug-and-play differentiable rewards from Vision-Language Models (VLMs) to guide image generation. Specify what/how to reward via prompts; backprop through the VLM with no fine-tuning. Includes anti-periodic loss functions that suppress the 16x16 pattern from image-token patching for cleaner textures.
-
Updated
Aug 20, 2025 - Python
Add this topic to your repo
To associate your repository with the alignprop topic, visit your repo's landing page and select "manage topics."