You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Dose-Response C3 with CLIP: Original composition (~1.21% unsafe), full scale

Text encoder ablation using CLIP (openai/clip-vit-large-patch14, 77 tokens) instead of default T5-Gemma-2B (256 tokens).


Condition	C3 — Original composition (~1.21% unsafe), full scale
Training set	~7.94M images