metadata
license: mit
library_name: sd15-flow-trainer
tags:
- geometric-deep-learning
- stable-diffusion
- ksimplex
- pentachoron
- flow-matching
- cross-attention-prior
base_model: sd-legacy/stable-diffusion-v1-5
pipeline_tag: text-to-image
KSimplex Geometric Attention Prior
Geometric cross-attention prior for SD1.5 using pentachoron (4-simplex) structures.
Architecture
| Component | Params |
|---|---|
| SD1.5 UNet (frozen) | 859,520,964 |
| Geo prior (trained) | 4,845,725 |
| Geo conditioner (trained) | 1,613,847 |
Simplex Configuration
| Parameter | Value |
|---|---|
| k (simplex dim) | 4 |
| Embedding dim | 32 |
| Feature dim | 768 |
| Stacked layers | 4 |
| Attention heads | 8 |
| Base deformation | 0.25 |
| Residual blend | learnable |
| Timestep conditioned | True |
GeoVocab Conditioning
| Parameter | Value |
|---|---|
| Gate dim | 17 |
| Patch feat dim | 256 |
| Num patches | 64 |
| Cross-attention | enabled |
| Cross-attn heads | 8 |
| Blend mode | learnable |
Usage
from sd15_trainer_geo.pipeline import load_pipeline
pipe = load_pipeline(geo_repo_id="AbstractPhil/sd15-geovocab-lora-prototype")
Training Info
- dataset: AbstractPhil/synthetic-characters (schnell_full_1_512)
- subdir: schnell_full_1_5e-5
- samples: 50000
- epochs: 10
- steps: 83330
- shift: 2.0
- base_lr: 5e-05
- min_snr_gamma: 5.0
- cfg_dropout: 0.1
- batch_size: 6
- geo_loss_weight: 0.01
- geovocab_lr_mult: 2.0
- clip_vae: AbstractPhil/geovae-proto/clip_vae/best_model.pt
- patch_maker: AbstractPhil/geovocab-patch-maker
- loss_final: 0.3035515168607235
License
MIT — AbstractPhil