Delete train_stage1.py, test_model.py

test_model.py

@@ -1,21 +0,0 @@
-"""Quick sanity test of LuminaRS without heavy deps."""
-import torch
-from luminars.model import LuminaRS
-from luminars.config import LuminaRSConfig
-
-def test():
-    cfg = LuminaRSConfig()
-    model = LuminaRS(cfg)
-    n = sum(p.numel() for p in model.parameters())
-    print(f"Total params: {n/1e6:.1f}M")
-    print(f"Trainable params: {sum(p.numel() for p in model.parameters() if p.requires_grad)/1e6:.1f}M")
-
-    bs, d, h, w = 2, cfg.latent_dim, cfg.latent_h, cfg.latent_w
-    z = torch.randn(bs, d, h, w)
-    text = torch.randn(bs, cfg.max_text_len, cfg.text_embed_dim)
-    t = torch.rand(bs)
-    out = model(z, text, t)
-    print(f"Forward OK, output shape: {out.shape}")
-
-if __name__ == "__main__":
-    test()

train_stage1.py

@@ -1,35 +0,0 @@
-"""
-LuminaRS Stage 1: Core Flow-Matching Training
-Trains the denoiser on art/illustration data with flow matching.
-Colab A100 compatible. Uses frozen pretrained VAE + CLIP.
-"""
-import os, math, torch, torch.nn.functional as F
-from torch.utils.data import DataLoader
-from datasets import load_dataset
-from torchvision import transforms
-from transformers import CLIPTextModel, CLIPTokenizer
-from diffusers import AutoencoderKL
-from luminars.model import LuminaRS
-from luminars.config import LuminaRSConfig
-
-# ── Flow Matching Loss ──────────────────────────────────────────────────
-def flow_matching_loss(model, vae, clip, z0, text_emb):
-    """Optimal-transport flow matching: v(x_t, t) = x1 - x0"""
-    B = z0.shape[0]
-    t = torch.rand(B, device=z0.device)
-    x1 = z0  # clean latent
-    x0 = torch.randn_like(z1)  # noise
-    # Linear interpolation
-    xt = (1 - t[:,None,None,None]) * x0 + t[:,None,None,None] * x1
-    # Target velocity (straight line)
-    v_target = x1 - x0
-    v_pred = model(xt, text_emb, t)
-    return F.mse_loss(v_pred, v_target)
-
-def flow_matching_loss(model, vae, clip, pixel_images, text_tokens):
-    """Full pipeline: image -> VAE encode -> flow matching."""
-    with torch.no_grad():
-        latents = vae.encode(pixel_images).latent_dist.sample()
-        latents = latents * vae.config.scaling_factor
-        text_emb = clip(text_tokens).last_hidden_state
-    return flow_matching_loss(model, vae, clip, latents, text_emb), latents, text_emb