Use adaptive CUDA latent upscale chunking

dumas_h3_latent_upscale.py

@@ -55,12 +55,16 @@ def _uses_cuda_model_upscale(param):
     return device == "cuda" and (mode == "model" or has_model_name)
 
 
-def _effective_temporal_params(param):
+def _effective_temporal_params(param, frame_count=None):
     chunk_length = int(param.get("chunk_length", 0) or 0)
     temporal_overlap = int(param.get("temporal_overlap", 0) or 0)
     if _uses_cuda_model_upscale(param):
-        chunk_length = CUDA_MODEL_CHUNK_LENGTH if chunk_length <= 0 else min(chunk_length, CUDA_MODEL_CHUNK_LENGTH)
-        temporal_overlap = min(max(0, temporal_overlap), max(0, chunk_length - 17))
+        if chunk_length <= 0:
+            chunk_length = 85
+            temporal_overlap = 17
+        if frame_count is not None and CUDA_MODEL_CHUNK_LENGTH < int(frame_count) <= chunk_length:
+            chunk_length = CUDA_MODEL_CHUNK_LENGTH
+            temporal_overlap = 0
     return chunk_length, temporal_overlap
 
 
@@ -771,13 +775,13 @@ def upscale_video_interp(video, param):
 def _upscale_video_temporal_chunks(video, param, upscaler):
     if video.device.type != "cpu":
         video = video.to(device="cpu", copy=True)
-    chunk_length, temporal_overlap = _effective_temporal_params(param)
+    t = int(video.shape[2])
+    frame_count = _frames_for_tokens(t)
+    chunk_length, temporal_overlap = _effective_temporal_params(param, frame_count)
     chunk_param = dict(param)
     chunk_param["chunk_length"] = chunk_length
     chunk_param["temporal_overlap"] = temporal_overlap
     anchor_strength = float(param.get("anchor_strength", 0.999) or 0.999)
-    t = int(video.shape[2])
-    frame_count = _frames_for_tokens(t)
     if chunk_length <= 0 or frame_count <= chunk_length:
         return upscaler(video, chunk_param)
 
@@ -918,10 +922,10 @@ class H3LatentUpscaleParams:
                     "tooltip": "Temporal fade schedule over each tile's sampling. Off keeps the fade fixed; narrowing shrinks it over steps; widening grows it over steps."}),
                 "dynamic_fade_min": ("INT", {"default": 32, "min": 0, "max": 4096, "step": 32,
                     "tooltip": "Minimum fade width used by dynamic_fade when it is enabled."}),
-                "chunk_length": ("INT", {"default": 17, "min": 17, "max": 100000, "step": 17,
-                    "tooltip": "Temporal chunk length for latent upscale. CUDA model upscale is capped to 17 internally so short long-video shots do not bypass splitting and OOM."}),
-                "temporal_overlap": ("INT", {"default": 0, "min": 0, "max": 100000, "step": 17,
-                    "tooltip": "Temporal overlap between latent chunks. CUDA model upscale uses 0 when capped to one H3 block to minimize peak VRAM."}),
+                "chunk_length": ("INT", {"default": 85, "min": 17, "max": 100000, "step": 17,
+                    "tooltip": "Temporal chunk length for latent upscale. CUDA model upscale keeps this when it splits the shot, but uses 17/0 if this would otherwise process the whole shot as one OOM-prone batch."}),
+                "temporal_overlap": ("INT", {"default": 17, "min": 0, "max": 100000, "step": 17,
+                    "tooltip": "Temporal overlap between latent chunks. 17 matches the upstream split example; CUDA model upscale drops overlap only for the emergency 17-frame guard path."}),
                 "resize_conditioning": ("BOOLEAN", {"default": False,
                     "tooltip": "Reserved for upstream split compatibility. Leave OFF unless you need the original fallback behavior."}),
                 "anchor_strength": ("FLOAT", {"default": 0.999, "min": 0.0, "max": 1.0, "step": 0.01,

tests/test_dumas_h3_longvideos.py

@@ -1171,8 +1171,8 @@ class DumasH3LongVideosHelperTests(unittest.TestCase):
         self.assertFalse(required["brightness_match"][1]["default"])
         self.assertEqual(required["dynamic_fade"][1]["default"], "off")
         self.assertEqual(required["dynamic_fade_min"][1]["default"], 32)
-        self.assertEqual(required["chunk_length"][1]["default"], 17)
-        self.assertEqual(required["temporal_overlap"][1]["default"], 0)
+        self.assertEqual(required["chunk_length"][1]["default"], 85)
+        self.assertEqual(required["temporal_overlap"][1]["default"], 17)
         self.assertFalse(required["resize_conditioning"][1]["default"])
         self.assertEqual(required["anchor_strength"][1]["default"], 0.999)
 
@@ -1262,14 +1262,25 @@ class DumasH3LongVideosHelperTests(unittest.TestCase):
         self.assertEqual(smaller["chunk_length"], 17)
         self.assertEqual(smaller["temporal_overlap"], 0)
 
-    def test_cuda_model_temporal_params_cap_saved_workflows(self):
+    def test_cuda_model_temporal_params_keep_splitting_saved_workflows(self):
         latent = importlib.import_module("dumas_h3_latent_upscale")
         chunk_length, temporal_overlap = latent._effective_temporal_params({
             "mode": "model",
             "device": "cuda",
             "chunk_length": 85,
             "temporal_overlap": 17,
-        })
+        }, frame_count=124)
+        self.assertEqual(chunk_length, 85)
+        self.assertEqual(temporal_overlap, 17)
+
+    def test_cuda_model_temporal_params_cap_single_chunk_saved_workflows(self):
+        latent = importlib.import_module("dumas_h3_latent_upscale")
+        chunk_length, temporal_overlap = latent._effective_temporal_params({
+            "mode": "model",
+            "device": "cuda",
+            "chunk_length": 85,
+            "temporal_overlap": 17,
+        }, frame_count=85)
         self.assertEqual(chunk_length, 17)
         self.assertEqual(temporal_overlap, 0)