| | { | | | "cost": [ | | | { | | | "device": "cuda", | | | "minutes": 10.1, | | | "name": "RTX 3090", | | | "vram_gb": 24 | | | } | | | ], | | | "description": ""Aurora" \u2014 an original three-shot alpine vignette on one unbroken score: a lone hiker stands beneath the first veil of green aurora at deep twilight, is dwarfed by the full dancing sky at the height of the night, and watches it fade into pink-and-gold dawn. The cuts happen inside one H3 ref2va generation (Z-Image draws the three boards; <Picture 1> is the first frame, <Picture 2> and <Picture 3> anchor the cuts at 00:02.700 and 00:05.400), so wind, breath, aurora hiss and the solo-piano score run continuously across the seams. First run 2026-09-09, job 3326d6699bf5.", | | | "id": "Aurora", | | | "seed": 42, | | | "variables": { | | | "board_1_launch": "wide cinematic photograph at dusk on a snowy alpine ridge: a lone hiker in a dark hooded coat walking up the last gentle rise of a snow crest, seen from behind and slightly below as a small dark figure against a deep blue and amber western sky, long blue shadows raking the snow, a plume of breath at the hood, the first sparse stars beginning to show overhead, photographic, sharp focus on the figure, huge sky above", | | | "board_2_gutter": "wide cinematic photograph at deep dusk on a snowy alpine ridge: a small dark hooded figure standing perfectly still on a crest of ice, seen from a distance against a cold lavender-blue sky with the first scattered stars, a thin spindrift of snow streaming off the ridge line, deep indigo shadow filling the valleys below, hushed and patient, photographic, sharp focus on the figure, immense empty sky above", | | | "board_3_shore": "wide cinematic photograph at deep twilight on a snowy alpine ridge: the small dark hooded silhouette of a lone hiker standing on a crest of ice beneath an immense clear starry sky, a faint first veil of green aurora rippling low along the horizon, deep indigo and blue tones, fine snow crystals glittering in the still air, photographic, sharp focus on the figure, huge empty sky above", | | | "height": 544, | | | "image_reference_type": "diffusers.modular_pipelines.minimax_h3.MiniMaxH3ImageReference", | | | "lora_adapter_name": "turbo", | | | "lora_model_name": "lightx2v/Minimax-h3-Turbo", | | | "lora_scale": 1, | | | "lora_weight_name": "minimax_h3_fl2v_turbo_8step_v1.0_bf16.safetensors", | | | "num_frames": 192, | | | "num_inference_steps": 9, | | | "prompt": "subject_definitions:\n<Subject 1> is the lone hiker in <Picture 1>, <Picture 2> and <Picture 3>: a small solitary figure in a dark hooded coat, seen always as a silhouette against the sky, standing on snow, face never visible.\n<Picture 1> is the first frame of [Shot 1]: the lone hiker walking up the last gentle rise of a snowy alpine crest at dusk, seen from behind and slightly below, deep blue and amber sky above, long blue shadows on the snow.\n<Picture 2> is a storyboard reference for [Shot 2], defining its wide distant view of the figure standing perfectly still on the crest under a cold lavender-blue sky with the first scattered stars, spindrift streaming off the ridge line.\n<Picture 3> is a storyboard reference for [Shot 3], defining its wide deep-twilight view: the hiker beneath an immense clear starry sky with the first faint veil of green aurora low on the horizon.\n\nsummary:\n[keyframe completion + reference generation] The target video follows <Subject 1> through an eight-second dusk in three shots: arriving up the last rise exactly as <Picture 1> shows it, standing still into the deepening cold staged as <Picture 2> plans it, and catching the first flicker of aurora staged as <Picture 3> plans it, under one continuous, sparing score.\n\nretention_analysis:\n<Subject 1> (appears in [Shot 1], [Shot 2], [Shot 3]): fully_preserved - the small dark hooded silhouette on the snow is kept exactly in every shot, only its posture and the light around it changing.\n<Picture 1> ([Shot 1] first frame): fully_preserved - the shot opens on its framing, the walking figure seen from behind, the dusk sky and the long blue shadows.\n<Picture 2> ([Shot 2] storyboard): partially_preserved - its wide distant view, the still figure, the cold lavender sky and the spindrift are kept, with the light newly deepening around the waiting figure.\n<Picture 3> ([Shot 3] storyboard): partially_preserved - its wide deep-twilight view, the immense starry sky, the faint veil low on the horizon and the hiker's place on the snow are kept, with the veil newly brightening and the figure newly still.\n\ndetailed_description:\nThe target video is in a realistic cinematic style, shot wide with the sky as the subject and the human figure kept small, moving from amber dusk blue through cold indigo to the first green of the aurora at deep twilight.\n[Shot 1] A wide shot opens exactly on <Picture 1>: a lone hiker in a dark hooded coat walks up the last gentle rise of a snowy alpine crest at dusk, seen from behind and slightly below, long blue shadows raking the snow, a plume of breath at the hood, the western sky amber fading into deep blue. With slow, even steps the figure crests the rise and stops, boots planting, the breath plume rising and dispersing, a pack strap settling against the coat. The camera holds a slow tracking shot that settles to stillness as the figure stops, the sky darkening almost imperceptibly around them.\n[Shot 2] At 00:02.700, the camera cuts to the wide distant view of <Picture 2>: the hiker stands perfectly still on the crest, small against a cold lavender-blue sky where the first scattered stars are appearing, a thin spindrift of snow streaming off the ridge line, the valleys below filling with indigo shadow. The figure does not move; only the breath plume, the drifting snow and the deepening of the light mark the passing of time. The camera holds a near-static wide shot through the long middle of the piece, patient and unhurried, as dusk settles into cold.\n[Shot 3] At 00:05.400, the camera cuts to the wide deep-twilight view of <Picture 3>: the hiker stands beneath an immense clear starry sky, the horizon a deep indigo line - and low along the northern horizon a faint first veil of green aurora appears, rippling gently upward. The figure's head lifts slightly as they notice it; the veil brightens and spreads just a little, holding its low place above the ridge. The camera holds the wide shot nearly still, drifting in very slightly toward the figure and the awakening sky, as the first light of the night begins.\n\noverall_soundscape:\n[Shot 1] opens on the crunch of boots on crusted snow and the tap of a pole fading as the figure crests the rise and stops, a strap settling, breath arriving as a steady mist, a low wind over the crest. [Shot 2] is the long hush of the wait: wind breathing over the ridge, spindrift hissing thinly across the ice, the faint tick of cooling fabric, near silence. [Shot 3] the wind falls away entirely and a faint high keening rises from the horizon with the first green veil, the hiker's slow exhale the only human sound.\n\nnon_diegetic_music:\nA sparse prelude for solo piano and soft sustained strings, quiet and unresolved, carries continuously across all three shots without : slow single notes over deep pedal tones that wait as much as they play, growing no louder as the sky darkens, and ending on one open, unresolved held chord as the first veil of green rises - a chord left deliberately unfinished, as if inviting what comes next.", | | | "reference_image_short_edge": 1024, | | | "weights_dtype": "{int4}", | | | "width": 960 | | | }, | | | "steps": [ | | | { | | | "name": "board_1_launch", |
| | "pipeline": { |
| | "arguments": { |
| | "guidance_scale": 0, | | | "height": 544, | | | "num_inference_steps": 9, | | | "prompt": "variable:board_1_launch", | | | "width": 960 | | | }, | | | "configuration": { | | | "component_type": "ZImagePipeline", | | | "offload": "sequential" | | | }, | | | "from_pretrained_arguments": { | | | "low_cpu_mem_usage": true, | | | "model_name": "Tongyi-MAI/Z-Image-Turbo", | | | "torch_dtype": "torch.bfloat16" | | | } | | | }, | | | "result": { | | | "content_type": "image/jpeg", | | | "embed_metadata": true | | | } | | | }, | | | { | | | "name": "board_2_gutter", |
| | "pipeline": { |
| | "arguments": { |
| | "guidance_scale": 0, | | | "height": 544, | | | "num_inference_steps": 9, | | | "prompt": "variable:board_2_gutter", | | | "width": 960 | | | }, | | | "configuration": { | | | "component_type": "ZImagePipeline", | | | "offload": "sequential" | | | }, | | | "from_pretrained_arguments": { | | | "low_cpu_mem_usage": true, | | | "model_name": "Tongyi-MAI/Z-Image-Turbo", | | | "torch_dtype": "torch.bfloat16" | | | } | | | }, | | | "result": { | | | "content_type": "image/jpeg", | | | "embed_metadata": true | | | } | | | }, | | | { | | | "name": "board_3_shore", |
| | "pipeline": { |
| | "arguments": { |
| | "guidance_scale": 0, | | | "height": 544, | | | "num_inference_steps": 9, | | | "prompt": "variable:board_3_shore", | | | "width": 960 | | | }, | | | "configuration": { | | | "component_type": "ZImagePipeline", | | | "offload": "sequential" | | | }, | | | "from_pretrained_arguments": { | | | "low_cpu_mem_usage": true, | | | "model_name": "Tongyi-MAI/Z-Image-Turbo", | | | "torch_dtype": "torch.bfloat16" | | | } | | | }, | | | "release_pipeline": true, | | | "result": { | | | "content_type": "image/jpeg", | | | "embed_metadata": true | | | } | | | }, | | | { | | | "name": "voyage", |
| | "pipeline": { |
| | "arguments": { |
| | "height": "variable:height", |
| | "num_frames": "variable:num_frames", | | | "num_inference_steps": "variable:num_inference_steps", | | | "output": [ | | | "videos", | | | "audio", | | | "sampling_rate" | | | ], |
| | "prompt": "variable:prompt", |
| | "references": [ |
| | { | | | "from_previous_result": "board_1_launch", | | | "reference_type": "variable:image_reference_type" | | | }, | | | { | | | "from_previous_result": "board_2_gutter", | | | "reference_type": "variable:image_reference_type" | | | }, | | | { | | | "from_previous_result": "board_3_shore", | | | "reference_type": "variable:image_reference_type" | | | } | | | ], | | | "width": "variable:width" | | | }, | | | "configuration": { | | | "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" | | | } | | | }, | | | "configs": { | | | "reference_image_short_edge": "variable:reference_image_short_edge" | | | }, | | | "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": "variable:weights_dtype" | | | }, | | | "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": "variable:weights_dtype" | | | }, | | | "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": "variable:lora_adapter_name", | | | "model_name": "variable:lora_model_name", | | | "scale": "variable:lora_scale", | | | "weight_name": "variable:lora_weight_name" | | | } | | | ] | | | }, | | | "result": { | | | "content_type": "video/mp4", | | | "fps": 24 | | | } | | | } | | | ] | | | } |