Tag
The paper introduces HN-CLIP, a method that uses the text encoder's text-text geometry to create adaptive similarity margins for dense-caption retrieval, addressing saturation issues in contrastive learning and improving performance over existing methods.
Release of an NVFP4-quantized uncensored MiniMax-H3 text encoder (Qwen3-VL-32B Heretic) that fits on a single 16GB GPU and serves as a drop-in replacement in ComfyUI workflows.
UR-BERT proposes a Romanized transcription-based text encoder for massively multilingual TTS, scaling to 495 languages by using universal Romanization and a speech token prediction objective to enhance phonetic alignment and generalization to unseen languages.
Ideogram-4 model repackaged for ComfyUI, including fp8 scaled diffusion models, Qwen3VL text encoder, and FLUX VAE.
This paper demonstrates that text-to-image diffusion transformer models primarily rely on token merging and word order from text encoders rather than full contextual embeddings, suggesting that the image model itself decodes complex linguistic structures.
This paper investigates how semantic information is distributed across textual tokens in text-to-image models, finding that information concentration and cross-item interactions significantly affect image generation alignment. The authors use patching techniques to demonstrate that simple encoding-stage interventions can improve alignment quality.