Reuse conditioning for refinement tiles

dumas_h3_longvideos.py

@@ -4076,6 +4076,52 @@ def _retarget_conditioning_spatial(cond, latent_h, latent_w):
     return out
 
 
+def _pad_to_h3_patch_size(tensor):
+    try:
+        import comfy.ldm.common_dit as common_dit
+        return common_dit.pad_to_patch_size(tensor, (1, 2, 2))
+    except Exception:
+        return tensor
+
+
+def _crop_conditioning_to_tile(cond, source_h, source_w, row, col, tile_h, tile_w):
+    """Crop H3 keyframe latents in existing conditioning for a spatial tile."""
+    out = []
+    for item in cond:
+        try:
+            tensor, data = item
+        except Exception:
+            out.append(item)
+            continue
+        nd = dict(data)
+        keyframes = nd.get("minimax_keyframes")
+        if keyframes:
+            cropped_keyframes = []
+            for keyframe in keyframes:
+                nkf = dict(keyframe)
+                latent_value = nkf.get("latent")
+                if latent_value is not None and len(getattr(latent_value, "shape", ())) >= 5:
+                    kh, kw = latent_value.shape[3], latent_value.shape[4]
+                    if kh != source_h or kw != source_w:
+                        b, c, t, h, w = latent_value.shape
+                        latent_value = torch.nn.functional.interpolate(
+                            latent_value.to(torch.float32).reshape(b * t, c, h, w),
+                            size=(source_h, source_w),
+                            mode="bilinear",
+                            align_corners=False,
+                        ).reshape(b, c, t, source_h, source_w).to(
+                            device=latent_value.device,
+                            dtype=latent_value.dtype,
+                        )
+                    nkf["latent"] = _pad_to_h3_patch_size(
+                        latent_value[:, :, :, row:row + tile_h, col:col + tile_w].contiguous()
+                    )
+                cropped_keyframes.append(nkf)
+            nd["minimax_keyframes"] = cropped_keyframes
+        out.append([tensor, nd])
+    return out
+
+
 def _latent_with_replaced_samples(template_latent, sampled_latent):
     """Reuse the original latent payload, but swap in freshly sampled tensors."""
     if not isinstance(template_latent, dict):
@@ -6828,12 +6874,10 @@ class H3LongVideos:
                         for col_index, c0 in enumerate(cols):
                             tc = tcols[col_index]
                             ovw = col_ovl[col_index]
-                            tile_target_w = int(tc) * 16
-                            tile_target_h = int(tr) * 16
-                            tile_cond, tile_latent = _build_shot_conditioning(
-                                clip, vae, prompt, tile_target_w, tile_target_h, ln, fps, handoff,
-                                ref_images=refs, ref_image_size=ref_image_size,
-                                ref_noise_aug=ref_noise_aug, audio_vae=audio_vae, silent=silent)
+                            tile_cond = _crop_conditioning_to_tile(
+                                upscale_cond, int(up_h), int(up_w), r0, c0, tr, tc
+                            )
+                            tile_latent = dict(upscale_latent) if isinstance(upscale_latent, dict) else {}
                             tile_video = upscaled_video[:, :, :, r0:r0 + tr, c0:c0 + tc].contiguous()
                             tr_s = tr + (tr % 2)
                             tc_s = tc + (tc % 2)