078b2eaf-f63c-4f03-bfc1-08a3093a0cf8
- Queued
- Aug 17, 2026, 11:17 AM
- Completed
- Aug 17, 2026, 11:17 AM
- Execution time
- 784 ms
- Outputs
- 0 · 0 B
- Inputs
- 1
- Cached nodes
- 1
Failure
Reference-to-video failed for asset(s): asset-20260817173814-kgsgg. See the API message logged just above. If it says the asset 'is not found', the asset was removed on BytePlus after enrollment (content review); the next run detects the dead cache entry and re-enrolls automatically.
Stack trace
File "/home/ec2-user/ComfyUI/execution.py", line 542, in execute
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)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ec2-user/ComfyUI/execution.py", line 341, in get_output_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)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ec2-user/ComfyUI/execution.py", line 315, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "/home/ec2-user/ComfyUI/execution.py", line 303, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "/home/ec2-user/ComfyUI/custom_nodes/ComfyUI-Seed-API/nodes/byteplus_video_node.py", line 924, in generate_video
raise ReferenceValidationError(
Outputs
0The run failed before producing any output.
Text prompts
1SCENE CONTEXT A woman stands alone on a quiet suburban street at golden hour beside a dark parked car, a lit cigarette in her lips. She takes one drag, speaks one quiet line, then slowly begins to cry. 10 seconds, one continuous shot. ACTIVE REFERENCES [Image 1]: woman in her late 30s, dark hair pulled back with loose strands, freckled skin, dark wool coat, cigarette between her lips, suburban street and dark car behind her. Face, hair, coat, and setting 100% match the reference. FIRST FRAME / BLOCKING First frame matches the reference: [Image 1] centered, facing camera, eyes on middle distance past the lens, blurred houses frame-left, dark car glass frame-right, low warm sun behind her right shoulder. FORMAT MODE One continuous shot, the camera does not cut on its own. CAMERA CU on the face, 29° portrait compression, shallow depth, eye-level, locked off with a barely perceptible slow push-in across all 10 seconds. Focus holds on her eyes. ACTION 0.0s to 3.5s — She raises her right hand, takes a slow deep drag, the cigarette tip flares orange, then lowers the hand out of frame and exhales a thin stream of smoke that drifts up through the sunlight. 3.5s to 6.0s — Her lips part and she speaks quietly, voice low and steady, accurate natural lip-sync: "This too shall pass." 6.0s to 10.0s — Her chin trembles once, her eyes glass over and well up, a single tear spills down her left cheek, her breath catches in a small silent hitch. She keeps looking past the camera. Hold on her wet eyes to the end frame. PERFORMANCE Emotion in muscles only: chin micro-tremor, slow welling tears, one swallow after the line, quiet weeping without sobbing. Pore-level skin realism, freckles intact, tear catching the golden light, living eyes with warm catch-lights. PHYSICS Smoke curls and thins naturally in still air. The tear gathers at the lower lid, breaks, and slides slowly down the cheek. Loose hair strands stir faintly. LIGHTING Low golden-hour sun from behind her right shoulder at 4000K, warm rim light on hair, soft fill on the face, background in soft haze, one consistent light throughout. AUDIO Quiet suburban ambience, soft drag and exhale, the line "This too shall pass" clear and foregrounded, then only her uneven breath. STYLE Photorealistic live action, cinematic, natural skin texture, fine film grain, real-time speed, 16:9. POSITIVE LOCKS Face, freckles, hairstyle, coat, and street stay 100% consistent with [Image 1] for all 10 seconds. Lip movement matches the spoken line exactly. One continuous take with the single slow push-in only.
Input media
1Source images and video this run consumed.