27d (edited) • 🛠️ Support/Help
Minimax H3 Director second pass workflow issue
Minimax H3 Director v1.4 second pass workflow issue
Hi Andy - I'm using the prompt override box for test prompts (Prompt override from socket is checked) - without the second pass, the preview and final output all work ok.
I'm setting 18 steps total; 14 steps for initial pass, then 4 for second refine stage.
If I check Enable Two Stage Sampling, it crashes after generating the 14 steps first pass (no video output). I'm guessing it should do 4 more passes, then move to the latent upscaler?
But the run crashes out; seems to be on the temporal chunks checkbox.
Doesn't matter whether the temporal chunking is checked or not, same crash.
Suggest the second refinement pass and the upscale be separated? (I might have it wrong, thought refinement passes were using the same first-pass model? Or is it trying to use the upscaler model to do the refinement and upscale at the same time?)
[INFO] got prompt
[INFO] [MuseMinimaxDirector] mode=Reference (Omni) — up to 7 images, 3 videos, 3 audio, 1376x768, seed=1111429277178777, seed_hunt=False, candidates=1, 1 chunk(s): ~15.0s (total 15.0s)
[INFO] [MuseMinimaxDirector] chunk 1/1, seed=1111429277178777, length=362 frames, video_carry=False, audio_carry=False, hybrid=False
[INFO] Requested to load MiniMaxH3VideoVAE
[INFO] Model MiniMaxH3VideoVAE prepared for dynamic VRAM loading. 4965MB Staged. 0 patches attached. Force pre-loaded 128 weights: 348 KB.
[INFO] Model MiniMaxH3VideoVAE prepared for dynamic VRAM loading. 4965MB Staged. 0 patches attached. Force pre-loaded 128 weights: 348 KB.
[INFO] Model MiniMaxH3VideoVAE prepared for dynamic VRAM loading. 4965MB Staged. 0 patches attached. Force pre-loaded 128 weights: 348 KB.
[INFO] Model MiniMaxH3VideoVAE prepared for dynamic VRAM loading. 4965MB Staged. 0 patches attached. Force pre-loaded 128 weights: 348 KB.
[INFO] Model MiniMaxH3VideoVAE prepared for dynamic VRAM loading. 4965MB Staged. 0 patches attached. Force pre-loaded 128 weights: 348 KB.
[INFO] Requested to load MiniMaxH3AudioVAE
[INFO] Model MiniMaxH3AudioVAE prepared for dynamic VRAM loading. 576MB Staged. 0 patches attached. Force pre-loaded 401 weights: 539 KB.
[INFO] Model MiniMaxH3AudioVAE prepared for dynamic VRAM loading. 576MB Staged. 0 patches attached. Force pre-loaded 401 weights: 539 KB.
[INFO] Requested to load MiniMaxH3TEModel_
[INFO] Model MiniMaxH3TEModel_ prepared for dynamic VRAM loading. 14956MB Staged. 0 patches attached. Force pre-loaded 410 weights: 4572 KB.
[INFO] VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
[INFO] VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
[INFO] Requested to load MiniMaxH3
[INFO] Model MiniMaxH3 prepared for dynamic VRAM loading. 19995MB Staged. 208 patches attached. Force pre-loaded 210 weights: 1175 KB.
100%|██████████████████████████████████████████████████████████████████████████████████| 14/14 [13:07<00:00, 56.28s/it]
[INFO] Comfy model compiler graph breaks: 4, rogues: 0
[ERROR] !!! Exception during processing !!! MinimaxH3LatentUpscaler3D.execute() got an unexpected keyword argument 'enable_temporal_chunking'
[ERROR] Traceback (most recent call last):
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
await process_inputs(input_dict, i)
result = f(**inputs)
File "E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\MiniMaxH3-Director-V1.2\muse_minimax_director.py", line 4058, in execute
images, audio, compiled_prompt_text, stage1_latent = _run_pass(seed, candidate_idx=0)
~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\MiniMaxH3-Director-V1.2\muse_minimax_director.py", line 3501, in _run_pass
upscaled_result = _unpack_node_result(_execute_comfy_node(
~~~~~~~~~~~~~~~~~~~^
MinimaxH3LatentUpscaler3D,
^^^^^^^^^^^^^^^^^^^^^^^^^^
...<7 lines>...
precision="fp16",
^^^^^^^^^^^^^^^^^
))[0]
^
File "E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\MiniMaxH3-Director-V1.2\muse_minimax_director.py", line 500, in _execute_comfy_node
return node_class.execute(**kwargs)
~~~~~~~~~~~~~~~~~~^^^^^^^^^^
TypeError: MinimaxH3LatentUpscaler3D.execute() got an unexpected keyword argument 'enable_temporal_chunking'
[INFO] Prompt executed in 00:13:32
1
8 comments
Minimax H3 Director second pass workflow issue
powered by
skool.com/muse-collective-7594
Cancel your AI subscriptions. Build local instead. Create AI characters & content with free, open-source tools, no monthly fees.
Suggested communities
Powered by