Views
No views yet
activation_dist checkpoint (one of three TPIPS models, each in its own repo — see
the table at the bottom). Code and full docs: https://github.com/adobe-research/TPIPS.-dist(a, 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 | -dist(a, b) |
| Fine-tuning | channel_lora (LoRA r=16, α=32) + per-layer text-MLP head |
| Probe layers | 20 evenly spaced LLM layers |
| Temperature | 0.0025 (applied at the probability step) |
Prompt X | Represent the similarity of the image based on X. |
pip install tpips1import tpips
2from PIL import Image
3
4model = tpips.load_model("activation_dist", device="cuda")
5a = Image.open("a.jpg").convert("RGB")
6b = Image.open("b.jpg").convert("RGB")
7
8distance = model.distance(a, b, factor="lighting") # lower is more similar| Model | Repo |
|---|---|
| Embedding (late fusion) | sywang/TPIPS-Embed-Qwen3VL-8B |
| Early Fusion | sywang/TPIPS-EarlyFusion-Qwen3VL-8B |
| Activation Distance | sywang/TPIPS-ActDiff-Qwen3VL-8B |