Add GIMM-VFI support (NeurIPS 2024) with single-pass arbitrary-timestep interpolation

Integrates GIMM-VFI alongside existing BIM/EMA/SGM models. Key feature: generates
all intermediate frames in one forward pass (no recursive 2x passes needed for 4x/8x).

- Vendor gimm_vfi_arch/ from kijai/ComfyUI-GIMM-VFI with device fixes
- Two variants: RAFT-based (~80MB) and FlowFormer-based (~123MB)
- Auto-download checkpoints from HuggingFace (Kijai/GIMM-VFI_safetensors)
- Three new nodes: Load GIMM-VFI Model, GIMM-VFI Interpolate, GIMM-VFI Segment Interpolate
- single_pass toggle: True=arbitrary timestep (default), False=recursive like other models
- ds_factor parameter for high-res input downscaling

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

gimm_vfi_arch/utils/utils.py

@@ -0,0 +1,52 @@
+from easydict import EasyDict as edict
+import torch.nn.functional as F
+
+class InputPadder:
+    """Pads images such that dimensions are divisible by divisor"""
+
+    def __init__(self, dims, divisor=16):
+        self.ht, self.wd = dims[-2:]
+        pad_ht = (((self.ht // divisor) + 1) * divisor - self.ht) % divisor
+        pad_wd = (((self.wd // divisor) + 1) * divisor - self.wd) % divisor
+        self._pad = [
+            pad_wd // 2,
+            pad_wd - pad_wd // 2,
+            pad_ht // 2,
+            pad_ht - pad_ht // 2,
+        ]
+
+    def pad(self, *inputs):
+        if len(inputs) == 1:
+            return F.pad(inputs[0], self._pad, mode="replicate")
+        else:
+            return [F.pad(x, self._pad, mode="replicate") for x in inputs]
+
+    def unpad(self, *inputs):
+        if len(inputs) == 1:
+            return self._unpad(inputs[0])
+        else:
+            return [self._unpad(x) for x in inputs]
+
+    def _unpad(self, x):
+        ht, wd = x.shape[-2:]
+        c = [self._pad[2], ht - self._pad[3], self._pad[0], wd - self._pad[1]]
+        return x[..., c[0] : c[1], c[2] : c[3]]
+def easydict_to_dict(obj):
+    if not isinstance(obj, edict):
+        return obj
+    else:
+        return {k: easydict_to_dict(v) for k, v in obj.items()}
+
+    
+class RaftArgs:
+    def __init__(self, small, mixed_precision, alternate_corr):
+        self.small = small
+        self.mixed_precision = mixed_precision
+        self.alternate_corr = alternate_corr
+
+    def _get_kwargs(self):
+        return {
+            "small": self.small,
+            "mixed_precision": self.mixed_precision,
+            "alternate_corr": self.alternate_corr
+        }