From bed5a51f8b83403629f40f0f82ea72e6df0a7d81 Mon Sep 17 00:00:00 2001
From: Vladimir Mandic <mandic00@live.com>
Date: Sun, 19 Jul 2026 10:52:55 +0200
Subject: [PATCH] fix skip processing

Signed-off-by: Vladimir Mandic <mandic00@live.com>
---
 extensions-builtin/sdnext-modernui     |  2 +-
 modules/processing_prompt.py           |  2 +-
 modules/seedvr/src/models/dit/patch.py | 34 ++++++++++++++++----------
 3 files changed, 23 insertions(+), 15 deletions(-)

diff --git a/extensions-builtin/sdnext-modernui b/extensions-builtin/sdnext-modernui
index b98735978..235e3f71a 160000
--- a/extensions-builtin/sdnext-modernui
+++ b/extensions-builtin/sdnext-modernui
@@ -1 +1 @@
-Subproject commit b987359783ddd8e217f1727f7505486db6d76a73
+Subproject commit 235e3f71ab2835d9340767552d16774967b2e643
diff --git a/modules/processing_prompt.py b/modules/processing_prompt.py
index 20ff18553..699e4fc94 100644
--- a/modules/processing_prompt.py
+++ b/modules/processing_prompt.py
@@ -23,7 +23,7 @@ def fix_prompt_batch(p, prompts, negative_prompts, prompts_2, negative_prompts_2
     if type(negative_prompts) is str:
         negative_prompts = [negative_prompts]
 
-    if hasattr(p, 'init_images') and p.init_images is not None and len(p.init_images) > 1:
+    if hasattr(p, 'init_images') and (p.init_images is not None) and (len(p.init_images) > 1) and not getattr(p, 'skip_processing', False):
         while len(prompts) < len(p.init_images):
             prompts.append(prompts[-1] if prompts else '')
         while len(negative_prompts) < len(p.init_images):
diff --git a/modules/seedvr/src/models/dit/patch.py b/modules/seedvr/src/models/dit/patch.py
index c273d0d5b..ccd4265ce 100644
--- a/modules/seedvr/src/models/dit/patch.py
+++ b/modules/seedvr/src/models/dit/patch.py
@@ -77,19 +77,23 @@ class NaPatchIn(PatchIn):
         self,
         vid: torch.Tensor,  # l c
         vid_shape: torch.LongTensor,
+        cache: Cache = Cache(disable=True),
     ) -> torch.Tensor:
+        cache = cache.namespace("patch")
+        vid_shape_before_patchify = cache("vid_shape_before_patchify", lambda: vid_shape)
         t, h, w = self.patch_size
         if not t == h == w == 1:
-            vid, vid_shape = na.rearrange(
-                vid, vid_shape, "(T t) (H h) (W w) c -> T H W (t h w c)", t=t, h=h, w=w
-            )
+            vid = na.unflatten(vid, vid_shape)
             for i in range(len(vid)):
-                if h > 1 and vid_shape[i, 1] % h != 0:
+                if t > 1 and vid_shape_before_patchify[i, 0] % t != 0:
+                    vid[i] = torch.cat([vid[i][:1]] * (t - vid[i].size(0) % t) + [vid[i]], dim=0)
+                if h > 1 and vid_shape_before_patchify[i, 1] % h != 0:
                     vid[i] = torch.cat([vid[i][:, :1]] * (h - vid[i].size(1) % h) + [vid[i]], dim=1)
-                if w > 1 and vid_shape[i, 2] % w != 0:
+                if w > 1 and vid_shape_before_patchify[i, 2] % w != 0:
                     vid[i] = torch.cat([vid[i][:, :, :1]] * (w - vid[i].size(2) % w) + [vid[i]], dim=2)
+                vid[i] = rearrange(vid[i], "(T t) (H h) (W w) c -> T H W (t h w c)", t=t, h=h, w=w)
             vid, vid_shape = na.flatten(vid)
-        # slice vid after patching in when using sequence parallelism
+        # slice vid after patchting in when using sequence parallelism
         vid = slice_inputs(vid, dim=0)
         if vid.dtype != self.proj.weight.dtype:
             vid = vid.to(self.proj.weight.dtype)
@@ -107,6 +111,8 @@ class NaPatchOut(PatchOut):
         torch.FloatTensor,
         torch.LongTensor,
     ]:
+        cache = cache.namespace("patch")
+        vid_shape_before_patchify = cache.get("vid_shape_before_patchify")
         t, h, w = self.patch_size
         if vid.dtype != self.proj.weight.dtype:
             vid = vid.to(self.proj.weight.dtype)
@@ -120,12 +126,14 @@ class NaPatchOut(PatchOut):
             cache=cache.namespace("vid"),
         )
         if not t == h == w == 1:
-            vid, vid_shape = na.rearrange(
-                vid, vid_shape, "T H W (t h w c) -> (T t) (H h) (W w) c", t=t, h=h, w=w
-            )
+            vid = na.unflatten(vid, vid_shape)
             for i in range(len(vid)):
-                if h > 1 and vid_shape[i, 1] % h != 0:
-                    vid[i] = vid[i][:, (h - vid_shape[i, 1] % h) :]
-                if w > 1 and vid_shape[i, 2] % w != 0:
-                    vid[i] = vid[i][:, :, (w - vid_shape[i, 2] % w) :]
+                vid[i] = rearrange(vid[i], "T H W (t h w c) -> (T t) (H h) (W w) c", t=t, h=h, w=w)
+                if t > 1 and vid_shape_before_patchify is not None and vid_shape_before_patchify[i, 0] % t != 0:
+                    vid[i] = vid[i][(t - vid_shape_before_patchify[i, 0] % t) :]
+                if h > 1 and vid_shape_before_patchify is not None and vid_shape_before_patchify[i, 1] % h != 0:
+                    vid[i] = vid[i][:, (h - vid_shape_before_patchify[i, 1] % h) :]
+                if w > 1 and vid_shape_before_patchify is not None and vid_shape_before_patchify[i, 2] % w != 0:
+                    vid[i] = vid[i][:, :, (w - vid_shape_before_patchify[i, 2] % w) :]
+            vid, vid_shape = na.flatten(vid)
         return vid, vid_shape