TPIPS — Embedding (late fusion) Text conditioned perceptual image similarity, built on Qwen/Qwen3 VL Embedding 8B. This repo holds the embedding checkpoint (one of three TPIPS models, each in its own repo — see the table at the bottom). Code and full docs: https://github.com/PeterWang512/TPIPS. Late fusion. Each (text, image) is encoded independently into an L2 normalised embedding. The pairwise score is cos(e a, e b) (higher = more similar). Odd one out probabilities are a softmax over the three "other pair" scores divided by the temperature; 2AFC compares the two reference candidate scores. The pairwise score is the model's raw output (temperature is applied at the probability step). Property Value Base model Qwen/Qwen3 VL Embedding 8B Pairwise score cos(e a, e b) Fine tuning LoRA (r=16, α=32) on the LLM layers Pooling last token Temperature 0.05 (applied at the probability step) Prompt X Represent the similarity of the image based on X. Usage flash attn is required (the model runs with flash attention 2); see the Installation guide for an easy matching wheel install. The TPIPS models Model Repo Embedding (late fusion) sywang/TPIPS Embed Qwen3VL 8B Early Fusion (R1/R2 register to…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy