文本到图像扩散模型中身份盆地的形态学分析
Morphological Addressing of Identity Basins in Text-to-Image Diffusion Models
AI总结：
通过形态学描述符和提示层面的音感结构，研究揭示了文本到图像扩散模型中身份盆地的系统性导航梯度，展示了身份稳定性和新视觉概念的生成。
摘要：
我们证明形态学压力在文本到图像生成管道的多个层次上创造了可导航的梯度。在研究1中，通过使用形态学描述符（如“铂金色”、“胎记”、“1950年代魅力”）可以导航稳定扩散1.5中的身份盆地，而无需目标名称或照片。一个自我蒸馏循环（通过描述符提示生成合成图像，然后在这些输出上训练LoRA）实现了通过ArcFace相似性测量的一致收敛到特定身份。训练后的LoRA不仅塑造了目标身份，还塑造了其反面：最大远离条件在基础SD1.5中产生“诡异”的结构崩溃，而配备LoRA的模型则产生“恐怖谷”输出——连贯但精确错误。在研究2中，我们扩展到提示层面的形态学。基于音感主题理论，我们从英语声音象征性簇（如“cr-”、“sn-”、“-oid”、“-ax”）生成200个新的无意义单词，并发现具有音感主题的候选者在视觉上比随机对照组更一致（均Purity@1 = 0.371 vs. 0.209，p<0.00001，Cohen's d=0.55）。三个候选词——“snudgeoid”、“crashax”和“broomix”——在没有训练数据污染的情况下实现了完美的视觉一致性（Purity@1 = 1.0），每个都从音感结构本身生成了一个独特的、连贯的视觉身份。这些研究证明了形态学结构——无论是特征描述符还是提示层面的语音形式——通过扩散模型潜在空间创造了系统化的导航梯度。我们记录了身份盆地中的相变、CFG不变的身份稳定性以及从子词声音模式中浮现的新视觉概念。
英文摘要：
We demonstrate that morphological pressure creates navigable gradients at multiple levels of the text-to-image generative pipeline. In Study~1, identity basins in Stable Diffusion 1.5 can be navigated using morphological descriptors -- constituent features like platinum blonde,'' beauty mark,'' and 1950s glamour'' -- without the target's name or photographs. A self-distillation loop (generating synthetic images from descriptor prompts, then training a LoRA on those outputs) achieves consistent convergence toward a specific identity as measured by ArcFace similarity. The trained LoRA creates a local coordinate system shaping not only the target identity but also its inverse: maximal away-conditioning produces eldritch'' structural breakdown in base SD1.5, while the LoRA-equipped model produces ``uncanny valley'' outputs -- coherent but precisely wrong. In Study~2, we extend this to prompt-level morphology. Drawing on phonestheme theory, we generate 200 novel nonsense words from English sound-symbolic clusters (e.g., \emph{cr-}, \emph{sn-}, \emph{-oid}, \emph{-ax}) and find that phonestheme-bearing candidates produce significantly more visually coherent outputs than random controls (mean Purity@1 = 0.371 vs.\ 0.209, p<0.00001p < 0.00001 p<0.00001, Cohen's d=0.55d = 0.55 d=0.55). Three candidates -- \emph{snudgeoid}, \emph{crashax}, and \emph{broomix} -- achieve perfect visual consistency (Purity@1 = 1.0) with zero training data contamination, each generating a distinct, coherent visual identity from phonesthetic structure alone. Together, these studies establish that morphological structure -- whether in feature descriptors or prompt-level phonological form -- creates systematic navigational gradients through diffusion model latent spaces. We document phase transitions in identity basins, CFG-invariant identity stability, and novel visual concepts emerging from sub-lexical sound patterns.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
