The image output from the interpolation nodes (FILM, Fortuna, etc) seem to be in half format, when they should be full float? If I don't use the interpolation nodes, the images can be saved with combo node, or viewed in preview image. I'm not sure what's going on.
ERROR:root:Traceback (most recent call last):
File "K:\ComfyUI_Main\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "K:\ComfyUI_Main\ComfyUI\execution.py", line 82, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "K:\ComfyUI_Main\ComfyUI\execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "K:\ComfyUI_Main\ComfyUI\comfy_extras\nodes_upscale_model.py", line 52, in upscale
s = comfy.utils.tiled_scale(in_img, lambda a: upscale_model(a), tile_x=tile, tile_y=tile, overlap=overlap, upscale_amount=upscale_model.scale, pbar=pbar)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\comfy\utils.py", line 418, in tiled_scale
ps = function(s_in).to(output_device)
File "K:\ComfyUI_Main\ComfyUI\comfy_extras\nodes_upscale_model.py", line 52, in <lambda>
s = comfy.utils.tiled_scale(in_img, lambda a: upscale_model(a), tile_x=tile, tile_y=tile, overlap=overlap, upscale_amount=upscale_model.scale, pbar=pbar)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\comfy_extras\chainner_models\architecture\RRDB.py", line 296, in forward
return self.model(x)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\container.py", line 217, in forward
input = module(input)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\conv.py", line 460, in forward
return self._conv_forward(input, self.weight, self.bias)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\conv.py", line 456, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Input type (struct c10::Half) and bias type (float) should be the same
Preview/Save Image
ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
File "K:\ComfyUI_Main\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "K:\ComfyUI_Main\ComfyUI\execution.py", line 82, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "K:\ComfyUI_Main\ComfyUI\execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "K:\ComfyUI_Main\ComfyUI\comfy_extras\nodes_upscale_model.py", line 52, in upscale
s = comfy.utils.tiled_scale(in_img, lambda a: upscale_model(a), tile_x=tile, tile_y=tile, overlap=overlap, upscale_amount=upscale_model.scale, pbar=pbar)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\comfy\utils.py", line 418, in tiled_scale
ps = function(s_in).to(output_device)
File "K:\ComfyUI_Main\ComfyUI\comfy_extras\nodes_upscale_model.py", line 52, in <lambda>
s = comfy.utils.tiled_scale(in_img, lambda a: upscale_model(a), tile_x=tile, tile_y=tile, overlap=overlap, upscale_amount=upscale_model.scale, pbar=pbar)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\comfy_extras\chainner_models\architecture\RRDB.py", line 296, in forward
return self.model(x)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\container.py", line 217, in forward
input = module(input)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\conv.py", line 460, in forward
return self._conv_forward(input, self.weight, self.bias)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\conv.py", line 456, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Input type (struct c10::Half) and bias type (float) should be the same
The image output from the interpolation nodes (FILM, Fortuna, etc) seem to be in half format, when they should be full float? If I don't use the interpolation nodes, the images can be saved with combo node, or viewed in preview image. I'm not sure what's going on.
ComfyUI commit: 74b7233f57301bb08c2b29fb420eeacf8757d41c I installed ComfyUI from the repo on a venv, I didn't use the portable.
Upscaling with Image Upscale (with model) node:
Preview/Save Image