You can deploy this model and start earning money today!

AbstractPhil/
sd15-geoflow-object-association

sd15-flow-trainer

geometric-deep-learning

cross-attention-prior

text-to-image

stable-diffusion-v1-5/stable-diffusion-v1-5

finetune

mit

Views

No views yet

Before

After one epoch

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

The geometric prior modulates CLIP encoder hidden states through 4-layer stacked k-simplex attention before they reach the 16 cross-attention blocks in the UNet.

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

Usage

python

from sd15_trainer_geo.pipeline import load_pipeline, load_geo_from_hub

# Load base SD1.5 + fresh geo prior
pipe = load_pipeline()

# Load trained geo weights from this repo
load_geo_from_hub(pipe, "AbstractPhil/sd15-geoflow-object-association")

# Or one-shot: load base + geo in one call
pipe = load_pipeline(geo_repo_id="AbstractPhil/sd15-geoflow-object-association")

Training Info

dataset: AbstractPhil/synthetic-object-relations (schnell_512_2)
samples: 50000
epochs: 1
steps: 8333
shift: 2.5
base_lr: 5e-05
min_snr_gamma: 5.0
cfg_dropout: 0.1
batch_size: 6
geo_loss_weight: 0.01
loss_final: 0.38474819749593736

License

MIT — AbstractPhil