geovocab v1: schnell_full_1_5e-5 — 1 epoch 50k synthetic-characters

README.md

@@ -0,0 +1,81 @@
+---
+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
+
+```python
+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**: 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
+- **geovocab_lr_mult**: 2.0
+- **clip_vae**: AbstractPhil/geovae-proto/clip_vae/best_model.pt
+- **patch_maker**: AbstractPhil/geovocab-patch-maker
+- **loss_final**: 0.32467847257852556
+
+## License
+
+MIT — [AbstractPhil](https://huggingface.co/AbstractPhil)

geo_conditioner.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5378fe04ae1d7fa45b417da8ecdc414f0dd61f483f851a51064a938df89b1e47
+size 6457596

geo_prior.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6077921ede4e807aa07698c82217e0ff1bbb9b9a518d939a6c3c533e6d4a518
+size 19391076

geovocab_config.json

@@ -0,0 +1,14 @@
+{
+  "gate_dim": 17,
+  "patch_feat_dim": 256,
+  "num_patches": 64,
+  "clip_vae_dim": 768,
+  "clip_vae_bottleneck": 256,
+  "deform_hidden": 128,
+  "deform_num_layers": 4,
+  "cross_attn_enabled": true,
+  "cross_attn_heads": 8,
+  "cross_attn_dim": 768,
+  "geo_blend_mode": "learnable",
+  "geo_blend_init": 0.0
+}

simplex_config.json

@@ -0,0 +1,16 @@
+{
+  "k": 4,
+  "edim": 32,
+  "feat_dim": 768,
+  "num_layers": 4,
+  "base_deformation": 0.25,
+  "learnable_deformation": true,
+  "timestep_conditioned": true,
+  "num_heads": 8,
+  "dropout": 0.0,
+  "cm_loss_weight": 0.01,
+  "vol_consistency_weight": 0.005,
+  "residual_blend": "learnable",
+  "initial_blend": 0.0,
+  "_base_repo": "sd-legacy/stable-diffusion-v1-5"
+}