4a1f5489-1313-4597-9ab2-284684d77a4f
- Queued
- Aug 17, 2026, 06:53 AM
- Completed
- Aug 17, 2026, 06:53 AM
- Execution time
- 878 ms
- Outputs
- 0 · 0 B
- Inputs
- 1
- Cached nodes
- 1
Failure
xAI API returned HTTP 400: {"code": "invalid-argument", "error": "1080p video resolution is not supported for reference-to-video requests."}
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-Grok-Imagine-Video/nodes.py", line 219, in run
return _submit_and_download(kwargs, "generation", payload, "grok_reference_to_video")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ec2-user/ComfyUI/custom_nodes/ComfyUI-Grok-Imagine-Video/nodes.py", line 305, in _submit_and_download
request_id = client.start_video_generation(payload)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ec2-user/ComfyUI/custom_nodes/ComfyUI-Grok-Imagine-Video/xai_client.py", line 88, in start_video_generation
data = self._request_json("POST", "/v1/videos/generations", json_body=payload)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ec2-user/ComfyUI/custom_nodes/ComfyUI-Grok-Imagine-Video/xai_client.py", line 171, in _request_json
raise XAIImagineError(f"xAI API returned HTTP {response.status_code}: {_response_text(response)}")
Outputs
0The run failed before producing any output.
Text prompts
1Starting frame <Image 1>: post-battle battlefield, dusty warm daylight. <Image 3> (Baahubali, dark leather cuirass, gold flame-horse emblem) frame-left. <Image 2> (Bhallaladeva, steel muscle cuirass, red dhoti, sword at hip) frame-right. <Image 4> (Kattappa, bald, grey beard, chainmail, mace) center background. Mahishmati army with yellow banners in dusty haze behind. Faces, costumes, blood, dust and lighting stay exactly consistent with <Image 1> throughout — no morphing. 0.0–3.0s: Camera very slow push-in on the frontal medium framing. <Image 2> turns his head toward <Image 3> with a small proud smile. <Image 3> has faint sadness in his eyes, draws one slow breath, then turns right to meet <Image 2>'s gaze. Eyes lock. <Image 4> watches, still. Dust drifts, banners sway. 3.0–7.0s: <Image 3> takes two grounded steps toward <Image 2> and kneels on one knee before him, head bowed, right fist pressing the sand, full warrior's respect. He speaks in Hindi, natural lip-sync: "Maharaj." Camera eases slightly lower with the kneel, both men in frame, <Image 2> standing tall. 7.0–11.0s: <Image 2> immediately grips <Image 3>'s shoulders with both hands and pulls him upright in one strong motion — real body weight in the lift. <Image 2> speaks in Hindi with a broad warm public smile, lip-sync: "Mere saamne sar mat jhukao." His hands stay on the shoulders a moment. <Image 4>'s eyes narrow subtly behind 11.0–15.0s: <Image 2> leans in closer, smile cooling, and speaks low, only for <Image 3>, near-murmur, lip-sync: "Praja dekh rahi hai." He releases and looks out toward the army. Camera slowly pushes in on <Image 3>'s face — a flicker of confusion, brow tightening a fraction, first shadow of doubt. Hold on his uneasy eyes. End frame: medium-close on <Image 3>, eyes fixed off-frame right, troubled, dusty golden light. Performance: <Image 3> — controlled sadness, genuine humble kneel, then micro-expression confusion, eyes do the acting. <Image 2> — surface warmth masking calculation; public smile broad, whisper cold. <Image 4> — silent watchful observer. Camera: one continuous take, no cuts — slow push-in, lower with kneel, rise with lift, final push-in to <Image 3>'s face. Smooth dolly only; no handheld, no zooms, no speed ramps, no slow motions. Environment: drifting dust haze, banners in mild wind, army in soft stillness, fine dust in sunlight, dust puffs at knee and steps. Audio: No background music, no score, no BGM of any kind. Only real diegetic sound — dry battlefield wind, banner cloth flutter, distant army ambience ound quality, no added music stings, no ambient drones
Input media
1Source images and video this run consumed.