ArtVentureX / comfyui-animatediff

AnimateDiff for ComfyUI
Apache License 2.0
698 stars 45 forks source link

indexError:list index out of range #34

Open Bearoar opened 1 year ago

Bearoar commented 1 year ago

Hi, Can someone help me with this : note:dont have cuda on my navida card, wondering if is this problme.

bellow is the info : got prompt 3 [AnimateDiff] - INFO - Injecting motion module with method legacy. [AnimateDiff] - INFO - Override beta schedule. loading new loading in lowvram mode 509.3894233703613 [AnimateDiff] - INFO - Restoring beta schedule. [AnimateDiff] - INFO - Ejecting motion module with method legacy. !!! Exception during processing !!! Traceback (most recent call last): File "F:\ComfyUI_windows_portable\ComfyUI\execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "F:\ComfyUI_windows_portable\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 "F:\ComfyUI_windows_portable\ComfyUI\execution.py", line 75, in map_node_over_list results.append(getattr(obj, func)(*slice_dict(input_data_all, i))) File "F:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-animatediff-main\animatediff\nodes.py", line 310, in animatediff_sample return super().sample( File "F:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1236, in sample return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise) File "F:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1206, in common_ksampler samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, File "F:\ComfyUI_windows_portable\ComfyUI\comfy\sample.py", line 81, in sample comfy.model_management.load_models_gpu([model] + models, comfy.model_management.batch_area_memory(noise.shape[0] noise.shape[2] noise.shape[3]) + inference_memory) File "F:\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 397, in load_models_gpu cur_loaded_model = loaded_model.model_load(lowvram_model_memory) File "F:\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 290, in model_load device_map = accelerate.infer_auto_device_map(self.real_model, max_memory={0: "{}MiB".format(lowvram_model_memory // (1024 1024)), "cpu": "16GiB"}) File "F:\ComfyUI_windows_portable\python_embeded\lib\site-packages\accelerate\utils\modeling.py", line 1033, in infer_auto_device_map tied_moduleindex = [i for i, (n, ) in enumerate(modules_to_treat) if n in tied_param][0] IndexError: list index out of range

artventuredev commented 1 year ago

What video card are you using? Can you share a screenshot of your current workflow?

Also please try to run the same workflow, but swap out the AnimateDiffSampler with normal KSampler, and update the batch_size in the EmptyLatent to the save with the frame_number. If the same workflow with KSampler can run, then you should be able to run with AnimateDiffSampler

Bearoar commented 1 year ago

screenshot it looks like this , actually, i just drug the 'simple.json' in to the work space, and it give me those error.

my card is navida k620, haha , just wanna to try the work flow, dont know what is going wrong.

i tried to change animatediffsampler with ksampler, it works well, when i switch it back, dont work

artventuredev commented 1 year ago

When switch to Ksampler, please also try with batch_size = 16

image