| { | |
| "cost_drivers": [ | |
| "total_frames", | |
| "f2", | |
| "f3", | |
| "f4" | |
| ], | |
| "description": "Inner Space, Episode One, end to end: three documentary lines generated in H3 against the approved audition take (kept verbatim as line one and used as the timbre reference for the rest), assembled into one narration, then laid over the five-shot cut with the score and the ducked world sound, and paired back to picture.", | |
| "id": "InnerSpaceFilm", | |
| "seed": 5, | |
| "shape": "sequence", | |
| "steps": [ | |
| { | |
| "name": "ref_still", | |
| "result": { | |
| "content_type": "image/png", | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "video": "asset:inner-space/shot-caverns.mp4" | |
| }, | |
| "command": "get_first_frame" | |
| } | |
| }, | |
| { | |
| "name": "line1", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audio": "asset:inner-space/vo-ref.wav", | |
| "peak_dbfs": -3 | |
| }, | |
| "command": "normalize_audio" | |
| } | |
| }, | |
| { | |
| "name": "vo2", | |
| "pipeline": { | |
| "arguments": { | |
| "height": 544, | |
| "num_frames": "variable:f2", | |
| "num_inference_steps": 9, | |
| "output": [ | |
| "videos", | |
| "audio", | |
| "sampling_rate" | |
| ], | |
| "prompt": "variable:p2", | |
| "references": [ | |
| { | |
| "from_previous_result": "ref_still", | |
| "reference_type": "diffusers.modular_pipelines.minimax_h3.MiniMaxH3ImageReference" | |
| }, | |
| { | |
| "from_file": "asset:inner-space/vo-ref.wav", | |
| "reference_type": "diffusers.modular_pipelines.minimax_h3.MiniMaxH3AudioReference" | |
| } | |
| ], | |
| "width": 960 | |
| }, | |
| "audio_scheduler": { | |
| "shift": 3 | |
| }, | |
| "configuration": { | |
| "cache": { | |
| "threshold": 0.1, | |
| "type": "first_block" | |
| }, | |
| "component_type": "ModularPipeline", | |
| "components": { | |
| "audio_vae": { | |
| "device": "cuda", | |
| "residency": "on_demand" | |
| }, | |
| "text_encoder": { | |
| "remove_modules": [ | |
| "lm_head" | |
| ] | |
| }, | |
| "text_encoder.model": { | |
| "group_offload": { | |
| "offload_type": "leaf_level" | |
| }, | |
| "truncate_layers": { | |
| "language_model.layers": 51 | |
| } | |
| }, | |
| "transformer_ref": { | |
| "group_offload": { | |
| "low_cpu_mem_usage": true, | |
| "num_blocks_per_group": 1, | |
| "offload_type": "block_level", | |
| "record_stream": true, | |
| "use_stream": true | |
| } | |
| }, | |
| "vae": { | |
| "device": "cuda", | |
| "residency": "on_demand" | |
| } | |
| }, | |
| "load_components": { | |
| "dtype": "torch.bfloat16", | |
| "quantization_config": { | |
| "text_encoder": { | |
| "arguments": { | |
| "dequantize_fp32": false, | |
| "modules_to_not_convert": [ | |
| ".model.visual", | |
| "lm_head" | |
| ], | |
| "quantization_device": "cuda", | |
| "return_device": "cpu", | |
| "weights_dtype": "{int4}" | |
| }, | |
| "configuration": { | |
| "config_type": "sdnq.SDNQConfig" | |
| } | |
| }, | |
| "transformer_ref": { | |
| "arguments": { | |
| "dequantize_fp32": false, | |
| "modules_to_not_convert": [ | |
| "proj_in", | |
| "audio_proj_in", | |
| "context_embedder", | |
| "time_embedder", | |
| "time_proj", | |
| "token_refiner", | |
| "norm_out", | |
| "proj_out", | |
| "audio_proj_out" | |
| ], | |
| "quantization_device": "cuda", | |
| "return_device": "cpu", | |
| "use_quantized_matmul": true, | |
| "weights_dtype": "{int4}" | |
| }, | |
| "configuration": { | |
| "config_type": "sdnq.SDNQConfig" | |
| } | |
| }, | |
| "vae": { | |
| "arguments": { | |
| "dequantize_fp32": false, | |
| "quant_conv": true, | |
| "quantization_device": "cuda", | |
| "return_device": "cpu", | |
| "use_quantized_matmul_conv": true, | |
| "weights_dtype": "{int8}" | |
| }, | |
| "configuration": { | |
| "config_type": "sdnq.SDNQConfig" | |
| } | |
| } | |
| } | |
| }, | |
| "pre_load_modules": [ | |
| "sdnq" | |
| ] | |
| }, | |
| "from_pretrained_arguments": { | |
| "model_name": "MiniMaxAI/MiniMax-H3", | |
| "workflow": "ref2va" | |
| }, | |
| "loras": [ | |
| { | |
| "adapter_name": "turbo", | |
| "alpha": null, | |
| "model_name": "lightx2v/Minimax-h3-Turbo", | |
| "scale": 1, | |
| "weight_name": "minimax_h3_ref2v_turbo_8step_v1.0_768p_bf16.safetensors" | |
| } | |
| ], | |
| "scheduler": { | |
| "shift": 12 | |
| } | |
| }, | |
| "result": { | |
| "content_type": "video/mp4", | |
| "fps": 24, | |
| "subfolder": "intermediate" | |
| } | |
| }, | |
| { | |
| "name": "vo3", | |
| "pipeline": { | |
| "arguments": { | |
| "height": 544, | |
| "num_frames": "variable:f3", | |
| "num_inference_steps": 9, | |
| "output": [ | |
| "videos", | |
| "audio", | |
| "sampling_rate" | |
| ], | |
| "prompt": "variable:p3", | |
| "references": [ | |
| { | |
| "from_previous_result": "ref_still", | |
| "reference_type": "diffusers.modular_pipelines.minimax_h3.MiniMaxH3ImageReference" | |
| }, | |
| { | |
| "from_file": "asset:inner-space/vo-ref.wav", | |
| "reference_type": "diffusers.modular_pipelines.minimax_h3.MiniMaxH3AudioReference" | |
| } | |
| ], | |
| "width": 960 | |
| }, | |
| "audio_scheduler": { | |
| "shift": 3 | |
| }, | |
| "configuration": { | |
| "cache": { | |
| "threshold": 0.1, | |
| "type": "first_block" | |
| }, | |
| "component_type": "ModularPipeline", | |
| "components": { | |
| "audio_vae": { | |
| "device": "cuda", | |
| "residency": "on_demand" | |
| }, | |
| "text_encoder": { | |
| "remove_modules": [ | |
| "lm_head" | |
| ] | |
| }, | |
| "text_encoder.model": { | |
| "group_offload": { | |
| "offload_type": "leaf_level" | |
| }, | |
| "truncate_layers": { | |
| "language_model.layers": 51 | |
| } | |
| }, | |
| "transformer_ref": { | |
| "group_offload": { | |
| "low_cpu_mem_usage": true, | |
| "num_blocks_per_group": 1, | |
| "offload_type": "block_level", | |
| "record_stream": true, | |
| "use_stream": true | |
| } | |
| }, | |
| "vae": { | |
| "device": "cuda", | |
| "residency": "on_demand" | |
| } | |
| }, | |
| "load_components": { | |
| "dtype": "torch.bfloat16", | |
| "quantization_config": { | |
| "text_encoder": { | |
| "arguments": { | |
| "dequantize_fp32": false, | |
| "modules_to_not_convert": [ | |
| ".model.visual", | |
| "lm_head" | |
| ], | |
| "quantization_device": "cuda", | |
| "return_device": "cpu", | |
| "weights_dtype": "{int4}" | |
| }, | |
| "configuration": { | |
| "config_type": "sdnq.SDNQConfig" | |
| } | |
| }, | |
| "transformer_ref": { | |
| "arguments": { | |
| "dequantize_fp32": false, | |
| "modules_to_not_convert": [ | |
| "proj_in", | |
| "audio_proj_in", | |
| "context_embedder", | |
| "time_embedder", | |
| "time_proj", | |
| "token_refiner", | |
| "norm_out", | |
| "proj_out", | |
| "audio_proj_out" | |
| ], | |
| "quantization_device": "cuda", | |
| "return_device": "cpu", | |
| "use_quantized_matmul": true, | |
| "weights_dtype": "{int4}" | |
| }, | |
| "configuration": { | |
| "config_type": "sdnq.SDNQConfig" | |
| } | |
| }, | |
| "vae": { | |
| "arguments": { | |
| "dequantize_fp32": false, | |
| "quant_conv": true, | |
| "quantization_device": "cuda", | |
| "return_device": "cpu", | |
| "use_quantized_matmul_conv": true, | |
| "weights_dtype": "{int8}" | |
| }, | |
| "configuration": { | |
| "config_type": "sdnq.SDNQConfig" | |
| } | |
| } | |
| } | |
| }, | |
| "pre_load_modules": [ | |
| "sdnq" | |
| ] | |
| }, | |
| "from_pretrained_arguments": { | |
| "model_name": "MiniMaxAI/MiniMax-H3", | |
| "workflow": "ref2va" | |
| }, | |
| "loras": [ | |
| { | |
| "adapter_name": "turbo", | |
| "alpha": null, | |
| "model_name": "lightx2v/Minimax-h3-Turbo", | |
| "scale": 1, | |
| "weight_name": "minimax_h3_ref2v_turbo_8step_v1.0_768p_bf16.safetensors" | |
| } | |
| ], | |
| "scheduler": { | |
| "shift": 12 | |
| } | |
| }, | |
| "result": { | |
| "content_type": "video/mp4", | |
| "fps": 24, | |
| "subfolder": "intermediate" | |
| } | |
| }, | |
| { | |
| "name": "vo4", | |
| "pipeline": { | |
| "arguments": { | |
| "height": 544, | |
| "num_frames": "variable:f4", | |
| "num_inference_steps": 9, | |
| "output": [ | |
| "videos", | |
| "audio", | |
| "sampling_rate" | |
| ], | |
| "prompt": "variable:p4", | |
| "references": [ | |
| { | |
| "from_previous_result": "ref_still", | |
| "reference_type": "diffusers.modular_pipelines.minimax_h3.MiniMaxH3ImageReference" | |
| }, | |
| { | |
| "from_file": "asset:inner-space/vo-ref.wav", | |
| "reference_type": "diffusers.modular_pipelines.minimax_h3.MiniMaxH3AudioReference" | |
| } | |
| ], | |
| "width": 960 | |
| }, | |
| "audio_scheduler": { | |
| "shift": 3 | |
| }, | |
| "configuration": { | |
| "cache": { | |
| "threshold": 0.1, | |
| "type": "first_block" | |
| }, | |
| "component_type": "ModularPipeline", | |
| "components": { | |
| "audio_vae": { | |
| "device": "cuda", | |
| "residency": "on_demand" | |
| }, | |
| "text_encoder": { | |
| "remove_modules": [ | |
| "lm_head" | |
| ] | |
| }, | |
| "text_encoder.model": { | |
| "group_offload": { | |
| "offload_type": "leaf_level" | |
| }, | |
| "truncate_layers": { | |
| "language_model.layers": 51 | |
| } | |
| }, | |
| "transformer_ref": { | |
| "group_offload": { | |
| "low_cpu_mem_usage": true, | |
| "num_blocks_per_group": 1, | |
| "offload_type": "block_level", | |
| "record_stream": true, | |
| "use_stream": true | |
| } | |
| }, | |
| "vae": { | |
| "device": "cuda", | |
| "residency": "on_demand" | |
| } | |
| }, | |
| "load_components": { | |
| "dtype": "torch.bfloat16", | |
| "quantization_config": { | |
| "text_encoder": { | |
| "arguments": { | |
| "dequantize_fp32": false, | |
| "modules_to_not_convert": [ | |
| ".model.visual", | |
| "lm_head" | |
| ], | |
| "quantization_device": "cuda", | |
| "return_device": "cpu", | |
| "weights_dtype": "{int4}" | |
| }, | |
| "configuration": { | |
| "config_type": "sdnq.SDNQConfig" | |
| } | |
| }, | |
| "transformer_ref": { | |
| "arguments": { | |
| "dequantize_fp32": false, | |
| "modules_to_not_convert": [ | |
| "proj_in", | |
| "audio_proj_in", | |
| "context_embedder", | |
| "time_embedder", | |
| "time_proj", | |
| "token_refiner", | |
| "norm_out", | |
| "proj_out", | |
| "audio_proj_out" | |
| ], | |
| "quantization_device": "cuda", | |
| "return_device": "cpu", | |
| "use_quantized_matmul": true, | |
| "weights_dtype": "{int4}" | |
| }, | |
| "configuration": { | |
| "config_type": "sdnq.SDNQConfig" | |
| } | |
| }, | |
| "vae": { | |
| "arguments": { | |
| "dequantize_fp32": false, | |
| "quant_conv": true, | |
| "quantization_device": "cuda", | |
| "return_device": "cpu", | |
| "use_quantized_matmul_conv": true, | |
| "weights_dtype": "{int8}" | |
| }, | |
| "configuration": { | |
| "config_type": "sdnq.SDNQConfig" | |
| } | |
| } | |
| } | |
| }, | |
| "pre_load_modules": [ | |
| "sdnq" | |
| ] | |
| }, | |
| "from_pretrained_arguments": { | |
| "model_name": "MiniMaxAI/MiniMax-H3", | |
| "workflow": "ref2va" | |
| }, | |
| "loras": [ | |
| { | |
| "adapter_name": "turbo", | |
| "alpha": null, | |
| "model_name": "lightx2v/Minimax-h3-Turbo", | |
| "scale": 1, | |
| "weight_name": "minimax_h3_ref2v_turbo_8step_v1.0_768p_bf16.safetensors" | |
| } | |
| ], | |
| "scheduler": { | |
| "shift": 12 | |
| } | |
| }, | |
| "result": { | |
| "content_type": "video/mp4", | |
| "fps": 24, | |
| "subfolder": "intermediate" | |
| } | |
| }, | |
| { | |
| "name": "r2", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "sample_rate": 44100, | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audio": "previous_result:vo2", | |
| "target_sample_rate": "variable:sample_rate" | |
| }, | |
| "command": "resample_audio" | |
| } | |
| }, | |
| { | |
| "name": "n2", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audio": "previous_result:r2", | |
| "peak_dbfs": -3 | |
| }, | |
| "command": "normalize_audio" | |
| } | |
| }, | |
| { | |
| "name": "r3", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "sample_rate": 44100, | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audio": "previous_result:vo3", | |
| "target_sample_rate": "variable:sample_rate" | |
| }, | |
| "command": "resample_audio" | |
| } | |
| }, | |
| { | |
| "name": "n3", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audio": "previous_result:r3", | |
| "peak_dbfs": -3 | |
| }, | |
| "command": "normalize_audio" | |
| } | |
| }, | |
| { | |
| "name": "r4", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "sample_rate": 44100, | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audio": "previous_result:vo4", | |
| "target_sample_rate": "variable:sample_rate" | |
| }, | |
| "command": "resample_audio" | |
| } | |
| }, | |
| { | |
| "name": "n4", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audio": "previous_result:r4", | |
| "peak_dbfs": -3 | |
| }, | |
| "command": "normalize_audio" | |
| } | |
| }, | |
| { | |
| "name": "join", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audios": [ | |
| "previous_result:line1", | |
| "previous_result:n2", | |
| "previous_result:n3", | |
| "previous_result:n4" | |
| ], | |
| "crossfade_ms": 0 | |
| }, | |
| "command": "crossfade_audio" | |
| } | |
| }, | |
| { | |
| "name": "vo", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "sample_rate": 44100, | |
| "subfolder": "final" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audio": "previous_result:join", | |
| "target_sample_rate": "variable:sample_rate" | |
| }, | |
| "command": "resample_audio" | |
| } | |
| }, | |
| { | |
| "name": "world", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audio": "variable:episode", | |
| "target_sample_rate": "variable:sample_rate" | |
| }, | |
| "command": "resample_audio" | |
| } | |
| }, | |
| { | |
| "name": "world_a", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audio": "previous_result:world", | |
| "fps": 24, | |
| "num_frames": "variable:grazers_start_frame", | |
| "start_frame": 0 | |
| }, | |
| "command": "slice_audio" | |
| } | |
| }, | |
| { | |
| "name": "world_b", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audio": "previous_result:world", | |
| "fps": 24, | |
| "num_frames": "variable:grazers_num_frames", | |
| "start_frame": "variable:grazers_start_frame" | |
| }, | |
| "command": "slice_audio" | |
| } | |
| }, | |
| { | |
| "name": "world_b_ducked", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audios": [ | |
| "previous_result:world_b" | |
| ], | |
| "gains": [ | |
| "variable:grazers_world_gain" | |
| ] | |
| }, | |
| "command": "mix_audio" | |
| } | |
| }, | |
| { | |
| "name": "world_c", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audio": "previous_result:world", | |
| "fps": 24, | |
| "num_frames": "variable:grazers_tail_frames", | |
| "start_frame": "variable:grazers_end_frame" | |
| }, | |
| "command": "slice_audio" | |
| } | |
| }, | |
| { | |
| "name": "world_ducked", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audios": [ | |
| "previous_result:world_a", | |
| "previous_result:world_b_ducked", | |
| "previous_result:world_c" | |
| ], | |
| "crossfade_ms": 0 | |
| }, | |
| "command": "crossfade_audio" | |
| } | |
| }, | |
| { | |
| "name": "score_slice", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audio": "variable:score", | |
| "fps": 24, | |
| "num_frames": "variable:total_frames", | |
| "start_frame": 0 | |
| }, | |
| "command": "slice_audio" | |
| } | |
| }, | |
| { | |
| "name": "score_faded", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audio": "previous_result:score_slice", | |
| "fade_in_ms": "variable:score_fade_in_ms", | |
| "fade_out_ms": "variable:score_fade_out_ms" | |
| }, | |
| "command": "fade_audio" | |
| } | |
| }, | |
| { | |
| "name": "score_rs", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audio": "previous_result:score_faded", | |
| "target_sample_rate": "variable:sample_rate" | |
| }, | |
| "command": "resample_audio" | |
| } | |
| }, | |
| { | |
| "name": "vo_fit", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audio": "previous_result:vo", | |
| "fps": 24, | |
| "num_frames": "variable:total_frames", | |
| "start_frame": 0 | |
| }, | |
| "command": "slice_audio" | |
| } | |
| }, | |
| { | |
| "name": "mixed", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audios": [ | |
| "previous_result:score_rs", | |
| "previous_result:vo_fit", | |
| "previous_result:world_ducked" | |
| ], | |
| "gains": [ | |
| "variable:score_gain", | |
| "variable:narration_gain", | |
| "variable:world_gain" | |
| ] | |
| }, | |
| "command": "mix_audio" | |
| } | |
| }, | |
| { | |
| "name": "balanced", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audio": "previous_result:mixed", | |
| "peak_dbfs": "variable:peak_dbfs" | |
| }, | |
| "command": "normalize_audio" | |
| } | |
| }, | |
| { | |
| "name": "ended", | |
| "result": { | |
| "content_type": "audio/wav", | |
| "subfolder": "intermediate" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audio": "previous_result:balanced", | |
| "fade_out_ms": "variable:film_fade_out_ms" | |
| }, | |
| "command": "fade_audio" | |
| } | |
| }, | |
| { | |
| "name": "film", | |
| "result": { | |
| "content_type": "video/mp4", | |
| "fps": 24, | |
| "subfolder": "final" | |
| }, | |
| "task": { | |
| "arguments": { | |
| "audio": "previous_result:ended", | |
| "fit": "video", | |
| "video": "variable:episode" | |
| }, | |
| "command": "pair_audio" | |
| } | |
| } | |
| ], | |
| "traits": [ | |
| "has-audio", | |
| "needs-input-media" | |
| ], | |
| "variables": { | |
| "episode": "asset:inner-space/episode.mp4", | |
| "f2": 209, | |
| "f3": 192, | |
| "f4": 226, | |
| "film_fade_out_ms": 1200, | |
| "grazers_end_frame": 333, | |
| "grazers_num_frames": 158, | |
| "grazers_start_frame": 175, | |
| "grazers_tail_frames": 508, | |
| "grazers_world_gain": 0.6, | |
| "narration_gain": 1.5, | |
| "p2": "subject_definitions:\n<Picture 1> is the visual reference for the setting: the dark, damp macro interior of a cave-like chamber with no person anywhere in it.\n<Audio 1> is the voice timbre and delivery reference for the narrator (S1): a deep, measured, experienced documentary voice, unhurried and resonant.\n\nsummary:\n[picture and audio reference] The target video holds on the dark macro interior shown in <Picture 1>, with no person in frame at any point. The narrator (S1) speaks in an off-screen voiceover whose voice timbre references <Audio 1>.\n\nretention_analysis:\n<Picture 1>: reference - the dark environment, its damp texture, its lighting and its palette are kept; its exact framing need not be.\n<Audio 1>: reference - only the timbre, the pitch and the unhurried delivery of the voice are referenced for (S1); none of its content or wording is reused.\n\ndetailed_description:\n[Shot 1] Live-action macro cinematography, a static shot holds on the dark, damp interior of <Picture 1> and nothing else enters the frame. No person is visible at any point. The deep, measured voice of an experienced documentary narrator (S1) says in an off-screen voiceover: <d>[English] Beneath the surface of every kitchen sponge lies a landscape no human eye has seen.</d> and remains entirely off-screen throughout, with no lips and no speaker ever appearing in the frame.\n\noverall_soundscape: A near-silent, acoustically dry room with nothing beyond the faintest room tone.\n\nnon_diegetic_music: N/A", | |
| "p3": "subject_definitions:\n<Picture 1> is the visual reference for the setting: the dark, damp macro interior of a cave-like chamber with no person anywhere in it.\n<Audio 1> is the voice timbre and delivery reference for the narrator (S1): a deep, measured, experienced documentary voice, unhurried and resonant.\n\nsummary:\n[picture and audio reference] The target video holds on the dark macro interior shown in <Picture 1>, with no person in frame at any point. The narrator (S1) speaks in an off-screen voiceover whose voice timbre references <Audio 1>.\n\nretention_analysis:\n<Picture 1>: reference - the dark environment, its damp texture, its lighting and its palette are kept; its exact framing need not be.\n<Audio 1>: reference - only the timbre, the pitch and the unhurried delivery of the voice are referenced for (S1); none of its content or wording is reused.\n\ndetailed_description:\n[Shot 1] Live-action macro cinematography, a static shot holds on the dark, damp interior of <Picture 1> and nothing else enters the frame. No person is visible at any point. The deep, measured voice of an experienced documentary narrator (S1) says in an off-screen voiceover: <d>[English] And in this world, the tide arrives when a hand reaches for the sink.</d> and remains entirely off-screen throughout, with no lips and no speaker ever appearing in the frame.\n\noverall_soundscape: A near-silent, acoustically dry room with nothing beyond the faintest room tone.\n\nnon_diegetic_music: N/A", | |
| "p4": "subject_definitions:\n<Picture 1> is the visual reference for the setting: the dark, damp macro interior of a cave-like chamber with no person anywhere in it.\n<Audio 1> is the voice timbre and delivery reference for the narrator (S1): a deep, measured, experienced documentary voice, unhurried and resonant.\n\nsummary:\n[picture and audio reference] The target video holds on the dark macro interior shown in <Picture 1>, with no person in frame at any point. The narrator (S1) speaks in an off-screen voiceover whose voice timbre references <Audio 1>.\n\nretention_analysis:\n<Picture 1>: reference - the dark environment, its damp texture, its lighting and its palette are kept; its exact framing need not be.\n<Audio 1>: reference - only the timbre, the pitch and the unhurried delivery of the voice are referenced for (S1); none of its content or wording is reused.\n\ndetailed_description:\n[Shot 1] Live-action macro cinematography, a static shot holds on the dark, damp interior of <Picture 1> and nothing else enters the frame. No person is visible at any point. The deep, measured voice of an experienced documentary narrator (S1) says in an off-screen voiceover: <d>[English] Every morning, the flood. Every evening, the drought. And still, they endure.</d> and remains entirely off-screen throughout, with no lips and no speaker ever appearing in the frame.\n\noverall_soundscape: A near-silent, acoustically dry room with nothing beyond the faintest room tone.\n\nnon_diegetic_music: N/A", | |
| "peak_dbfs": -1.5, | |
| "sample_rate": 44100, | |
| "score": "asset:inner-space/score.mp3", | |
| "score_fade_in_ms": 800, | |
| "score_fade_out_ms": 2500, | |
| "score_gain": 0.45, | |
| "total_frames": 841, | |
| "world_gain": 0.9 | |
| } | |
| } |
Xet Storage Details
- Size:
- 27.8 kB
- Xet hash:
- e003210d4e7809a5f47dff81d26d83ded083a8fad365b21e83b1af8d397092c7
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.