{ "created_utc": "2026-09-17T20:08:14Z", "variants": [ { "id": "base50", "label": "Original Ref2VA · 50 NFE", "nfe": 50, "adapter_kind": "none", "video_shift": 12.0, "audio_shift": 3.0, "sampler": "rectified-flow Euler (eta=0)", "base": "MiniMaxAI/MiniMax-H3 transformer_ref", "base_revision": "42ed227ee7df40d41602854ae760620d6eb651fe", "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-H3", "shared_components_revision": "42ed227ee7df40d41602854ae760620d6eb651fe", "short_label": "原版 H3 Ref2VA" }, { "id": "pdd8", "label": "Alibaba PAI PDD · 8 NFE", "nfe": 8, "adapter_kind": "pdd", "video_shift": 12.0, "audio_shift": 3.0, "sampler": "PDD parallel decoder on Euler flow grids", "lora_sha256": "111c82e669f6e20e628228172edf39395f1a9fc3ad049793895e542c0f55b18c", "base": "MiniMaxAI/MiniMax-H3 transformer_ref", "source_url": "https://huggingface.co/alibaba-pai/MiniMax-H3-Acc-LoRAs", "shared_components_revision": "42ed227ee7df40d41602854ae760620d6eb651fe", "base_revision": "42ed227ee7df40d41602854ae760620d6eb651fe", "lora_filename": "MiniMax-H3-Ref2VA-Acc-8Step.safetensors", "lora_revision": "335001fb9e5455d68a0caa18ec2e319072150328", "short_label": "Alibaba PAI · PDD" }, { "id": "lightx8", "label": "LightX2V Ref2VA v1.0 · 8 NFE", "nfe": 8, "adapter_kind": "lightx2v", "lora_alpha": 8, "video_shift": 6.0, "audio_shift": 3.0, "sampler": "rectified-flow Euler (eta=0)", "lora_sha256": "9bac880b1a5d7ac052171cf6cce769f0cceaaa42ffa51de4b8e41143a2bdd2d2", "base": "MiniMaxAI/MiniMax-H3 transformer_ref", "source_url": "https://huggingface.co/lightx2v/Minimax-h3-Turbo", "shared_components_revision": "42ed227ee7df40d41602854ae760620d6eb651fe", "base_revision": "42ed227ee7df40d41602854ae760620d6eb651fe", "lora_filename": "minimax_h3_ref2v_turbo_8step_v1.0_768p_bf16.safetensors", "lora_revision": "3ec17a324ced54151364f24f8b5fb6bf7e26414f", "lora_download_url": "https://huggingface.co/lightx2v/Minimax-h3-Turbo/resolve/3ec17a324ced54151364f24f8b5fb6bf7e26414f/minimax_h3_ref2v_turbo_8step_v1.0_768p_bf16.safetensors", "short_label": "LightX2V · Ref2VA v1.0" }, { "id": "vdn8", "label": "drbaph VDN-H3 extract · 8 NFE", "nfe": 8, "adapter_kind": "comfy", "video_shift": 12.0, "audio_shift": 3.0, "sampler": "rectified-flow Euler (eta=0)", "lora_sha256": "04f3ebbc2704dc6d8fded7e9cd9091446e47681c3c66cc27b17a1c5e071812b4", "base": "MiniMaxAI/MiniMax-H3 transformer_ref", "source_url": "https://huggingface.co/drbaph/MiniMax-H3-Turbo-Lora-ComfyUI", "caveat": "社区从 VDN-H3 提取的 8-step LoRA，采用作者声明兼容原版 Ref2VA 的主文件；本页使用 dense attention，不是原生 VDN 混合注意力模型。保留完整 AdaLN 适配及 FP32 LoRA 参数。", "shared_components_revision": "42ed227ee7df40d41602854ae760620d6eb651fe", "base_revision": "42ed227ee7df40d41602854ae760620d6eb651fe", "lora_filename": "minimax_h3_dmd_8step_turbo.safetensors", "lora_revision": "633e6c48cd05f7800e2cb2c007b5c9023b92c576", "lora_download_url": "https://huggingface.co/drbaph/MiniMax-H3-Turbo-Lora-ComfyUI/resolve/633e6c48cd05f7800e2cb2c007b5c9023b92c576/experimental/minimax_h3_dmd_8step_turbo.safetensors", "short_label": "drbaph · VDN 提取版" }, { "id": "rzgar8", "label": "rzgar Motion Enhancer · 8 NFE", "nfe": 8, "adapter_kind": "comfy", "video_shift": 6.0, "audio_shift": 3.0, "sampler": "rectified-flow Euler (eta=0)", "lora_sha256": "7cc07a2cecc00a25e76fe92f673c9b6823e1e8539df642301233842d77b0bf78", "base": "MiniMaxAI/MiniMax-H3 transformer_ref", "source_url": "https://huggingface.co/rzgar/minimax-h3_ref2va_8Step_motion_enhancer", "caveat": "作者主要面向成人内容相关的人体／动作微调；本页只测试非成人通用任务，不评价其目标领域表现。基于 LightX2V Ref2VA v1.0 768p，按作者要求单独加载，没有再叠加原 LightX2V LoRA。", "shared_components_revision": "42ed227ee7df40d41602854ae760620d6eb651fe", "base_revision": "42ed227ee7df40d41602854ae760620d6eb651fe", "lora_filename": "minimax-h3_ref2va_8Step_motion_enhancer.safetensors", "lora_revision": "8f7cb74cec9eb458b9a9298e1e428195579838dc", "lora_download_url": "https://huggingface.co/rzgar/minimax-h3_ref2va_8Step_motion_enhancer/resolve/8f7cb74cec9eb458b9a9298e1e428195579838dc/minimax-h3_ref2va_8Step_motion_enhancer.safetensors", "short_label": "rzgar · Motion Enhancer" }, { "id": "rkss8", "label": "Rkss DARE-TIES pruned + hybrid b20–49 · 8 NFE", "nfe": 8, "adapter_kind": "comfy", "video_shift": 12.0, "audio_shift": 3.0, "sampler": "rectified-flow Euler (eta=0)", "lora_sha256": "063df5592549161ff62a1e29ef49978625ee5060eda7d97edfa631bd9aa713b1", "hybrid_sha256": "8320246da06e5aae94988dc1ab336b19ebf2491b4393a330fb33bafca39f9d9a", "base": "smhfacct FL2VA–Ref2VA hybrid b20–49 INT8 ConvRot", "source_url": "https://huggingface.co/Rkss/Minimax_h3_fl2v_lightx2v_turbo_4to8step_768p_v4_step600_dareties_native", "caveat": "作者发布的 pruned 版（208 组骨干适配，已去掉 AdaLN 适配），搭配推荐的 b20–49 曲线 AdaLN / INT8 混合底模。不是同底模消融。使用 Comfy Kitchen 动态 INT8 运算和未融合 LoRA；不是原生 ComfyUI 性能测试。选择 Euler flow 网格，未采用可选 Beta57；另一 curve-ported 文件因目标基底不匹配未混用。", "shared_components_revision": "42ed227ee7df40d41602854ae760620d6eb651fe", "lora_filename": "minimax_h3_fl2v_lightx2v_turbo_4to8step_v0.1-v1.0_768p_v4_step600_dareties_fro095_pruned.safetensors", "lora_revision": "5934559ab8004be7aaae3f2ec8eeee9237149142", "lora_download_url": "https://huggingface.co/Rkss/Minimax_h3_fl2v_lightx2v_turbo_4to8step_768p_v4_step600_dareties_native/resolve/5934559ab8004be7aaae3f2ec8eeee9237149142/minimax_h3_fl2v_lightx2v_turbo_4to8step_v0.1-v1.0_768p_v4_step600_dareties_fro095_pruned.safetensors", "hybrid_filename": "minimax_h3_hybrid_fl2va_ref2va_b20-49-int8.safetensors", "hybrid_revision": "a36feb17fbd1f20ff4bdd509ccd07e2b7b585a38", "hybrid_download_url": "https://huggingface.co/smhfacct/Minimax-H3-fl2va-ref2va-hybrid-models/resolve/a36feb17fbd1f20ff4bdd509ccd07e2b7b585a38/minimax_h3_hybrid_fl2va_ref2va_b20-49-int8.safetensors", "short_label": "Rkss · DARE-TIES pruned" } ], "protocol": { "base_nfe": 50, "accelerated_nfe": 8, "shared_explicit_video_audio_noise": true, "target_resolution": "768p", "reference_resize_mode": "match", "attention": "FlashAttention 3 dense", "note": "Public-case qualitative comparison; not a held-out benchmark. Provider showcase outputs are not the local Base50 oracle." }, "completed_outputs": 60, "cases": [ { "id": "cyber_duel", "order": 1, "original_number": 6, "title": "雨夜双猎人交锋", "evaluation_axes": [ "双人物身份", "武器归属", "指定街景", "动作接触" ], "seed": 20260917, "source": "LightX2V public Ref2VA test set", "source_url": "https://github.com/ModelTC/Minimax-H3-Turbo/blob/main/examples/prompts_ref2va_test.json", "source_case_index": 1, "prompt": "subject_definitions:\n is the long-haired East Asian female hunter in , preserving her face, long wet black hair, black leather combat suit, tattered black cloak, black gloves, and single silver short blade.\n is the East Asian female tech hunter in , preserving her face, short black hair, white fox mask with red markings, black trench coat with cyan circuit lines, black boots, and single blue energy dagger.\n is the rainy cyberpunk intersection in , preserving its skyscrapers, giant blue-purple holographic billboard, neon signs, wet reflective asphalt, rain, and drifting fog.\n\nsummary:\n[reference generation] In one continuous 5.1667-second cinematic shot, and begin in a tense standoff inside , charge across the wet street, exchange one fast blade combination, and end locked blade-to-blade in a burst of blue energy.\n\nretention_analysis:\n (appears throughout): fully_preserved - retain the same face, long hair, black combat suit, cloak, body proportions, and one silver blade.\n (appears throughout): fully_preserved - retain the same face, short hair, fox mask, cyan-lit trench coat, body proportions, and one energy dagger.\n (appears throughout): fully_preserved - retain the wet intersection, billboard, neon palette, rain, fog, and reflective pavement.\n\ndetailed_description:\nPhotorealistic live-action cyberpunk action cinema, 16:9, high contrast purple-and-cyan night lighting, heavy rain, physically coherent motion, and stable identities. One continuous shot with no cuts, no duplicate people, no duplicate weapons, no costume changes, no gore, and no readable text.\n\n[Shot 1, 00:00.000-00:01.200] A low wide camera frames both fighters five meters apart on the rain-soaked street. crouches on frame left with her silver blade held low; stands on frame right with the blue energy dagger raised. Rain streaks through the holographic light and fog crosses the reflective road.\n\n[Shot 1, 00:01.200-00:03.600] Both women burst forward. The camera tracks sideways at waist height as 's cloak opens behind her. She makes one upward diagonal slash; sidesteps and blocks with the energy dagger. A compact blue-white spark and a ring of displaced droplets mark the impact. answers with one horizontal counter, which deflects with the flat of her blade.\n\n[Shot 1, 00:03.600-00:05.166] They rotate once around their joined weapons and stop in a close blade lock, faces and costumes still distinct. Cyan electricity crawls briefly across the crossed blades while rain runs from the fox mask and black cloak. The camera settles into a medium two-shot as the billboard flickers behind them and both hold the unresolved confrontation.\n\noverall_soundscape:\nHeavy rain, wet footfalls, two sharp blade impacts, controlled fabric movement, electrical crackle, distant traffic, and a low thunder roll. No dialogue.\n\nnon_diegetic_music:\nA dark electronic pulse rises through the charge and stops on the final blade lock.\n", "prompt_sha256": "9ff8d4e865a22faf4b9c014c225069227f88eaa96c078993fa40560bf1ae2ea4", "width": 1344, "height": 768, "fps": 24, "num_frames": 124, "duration_seconds": 5.166666666666667, "source_duration_seconds": 5.1666666667, "reference_category": "multi", "reference_resize_mode": "match", "noise_sha256": { "video": "2fc6ca72960c7a55da99a05475370558d51cbf7e095d4d2d3149d094a75c7d3b", "audio": "93539e5d8f7c8fa64f085483e2ee48b4c3c98947d41906a69941ac7a1cc71445" }, "references": [ { "type": "image", "source_url": "https://raw.githubusercontent.com/ModelTC/Minimax-H3-Turbo/main/examples/ref2va_testset/ref2va_test_1_1.jpg", "sha256": "1665c52d9e20ace593cbc30d1e17b5cf996ad25a59c7f1890d636711da93dbd3", "metadata": { "programs": [], "stream_groups": [], "streams": [ { "codec_type": "video", "width": 2560, "height": 1440, "r_frame_rate": "25/1", "duration": "0.040000" } ], "format": { "duration": "0.040000" } }, "url": "references/cyber_duel/reference_01.jpg", "label": "Picture / Image 1" }, { "type": "image", "source_url": "https://raw.githubusercontent.com/ModelTC/Minimax-H3-Turbo/main/examples/ref2va_testset/ref2va_test_1_2.jpg", "sha256": "df77cc201252e90cb828132863d4126c4d62d512f79299ec2651bcc9be8c5b1f", "metadata": { "programs": [], "stream_groups": [], "streams": [ { "codec_type": "video", "width": 2560, "height": 1440, "r_frame_rate": "25/1", "duration": "0.040000" } ], "format": { "duration": "0.040000" } }, "url": "references/cyber_duel/reference_02.jpg", "label": "Picture / Image 2" }, { "type": "image", "source_url": "https://raw.githubusercontent.com/ModelTC/Minimax-H3-Turbo/main/examples/ref2va_testset/ref2va_test_1_3.jpg", "sha256": "82cdb7a20d6ec0d7c6c396cc8e99d3f5fe49a2f67f7c3e5e75d45102f4a91062", "metadata": { "programs": [], "stream_groups": [], "streams": [ { "codec_type": "video", "width": 2560, "height": 1440, "r_frame_rate": "25/1", "duration": "0.040000" } ], "format": { "duration": "0.040000" } }, "url": "references/cyber_duel/reference_03.jpg", "label": "Picture / Image 3" } ], "results": { "base50": { "url": "media/cyber_duel/base50.mp4", "poster": "posters/cyber_duel/base50.jpg", "metadata_url": "data/cyber_duel/base50.json", "generation_seconds": 478.3103520567529, "context_parallel_degree": 1, "execution_mode": "fsdp_replicated_sample", "independent_samples": 1, "conditioning_cache_hits": 0, "actual_forward_count": 50, "sha256": "d25d8012e3c68b7ef1443ae68d986f8103cc04caa65e46bb7c39cc60a0f21067" }, "pdd8": { "url": "media/cyber_duel/pdd8.mp4", "poster": "posters/cyber_duel/pdd8.jpg", "metadata_url": "data/cyber_duel/pdd8.json", "generation_seconds": 152.99335530796088, "context_parallel_degree": 1, "execution_mode": "fsdp_replicated_sample", "independent_samples": 1, "conditioning_cache_hits": 0, "actual_forward_count": 8, "sha256": "0f1283b2daa577f580e0b32f50af52c0bec8412e883c21a1c68adaf3b097c4b8" }, "lightx8": { "url": "media/cyber_duel/lightx8.mp4", "poster": "posters/cyber_duel/lightx8.jpg", "metadata_url": "data/cyber_duel/lightx8.json", "generation_seconds": 147.22537825093605, "context_parallel_degree": 1, "execution_mode": "fsdp_replicated_sample", "independent_samples": 1, "conditioning_cache_hits": 0, "actual_forward_count": 8, "sha256": "edf7b90101331ea2a86c5aa0856444af43d7261fbb1c8ceffaf3d8a14f79b6f1" }, "vdn8": { "url": "media/cyber_duel/vdn8.mp4", "poster": "posters/cyber_duel/vdn8.jpg", "metadata_url": "data/cyber_duel/vdn8.json", "generation_seconds": 291.87067440804094, "context_parallel_degree": 1, "execution_mode": "fsdp_sample_parallel", "independent_samples": 2, "conditioning_cache_hits": 2, "actual_forward_count": 8, "sha256": "23f1afe6ebc2a34b9e77f5c93d81ff7445939aa5e1990a14bb0b77488f2253b5" }, "rzgar8": { "url": "media/cyber_duel/rzgar8.mp4", "poster": "posters/cyber_duel/rzgar8.jpg", "metadata_url": "data/cyber_duel/rzgar8.json", "generation_seconds": 252.20793965598568, "context_parallel_degree": 1, "execution_mode": "fsdp_sample_parallel", "independent_samples": 2, "conditioning_cache_hits": 2, "actual_forward_count": 8, "sha256": "134785dce34a6c838ce23bd5f84d3eb4e049ff613e515d41c17ebdf50ddca7dc" }, "rkss8": { "url": "media/cyber_duel/rkss8.mp4", "poster": "posters/cyber_duel/rkss8.jpg", "metadata_url": "data/cyber_duel/rkss8.json", "generation_seconds": 971.4409368513152, "context_parallel_degree": 1, "execution_mode": "fsdp_sample_parallel", "independent_samples": 8, "conditioning_cache_hits": 2, "actual_forward_count": 8, "sha256": "8b7f0e667b1a3cb04e6c43b6b9aab6c8b8d537ba36773ab0ac4e655e78f3e79e" } }, "prompt_url": "data/cyber_duel/prompt.txt" }, { "id": "day_to_night", "order": 2, "original_number": 4, "title": "白天改夜晚", "evaluation_axes": [ "光照编辑", "主体与场景保持", "动作保留" ], "seed": 20260917, "source": "fal public H3 showcase (not an open-weight baseline)", "source_url": "https://fal.ai/learn/devs/minimax-h3-prompting-guide", "source_title": "Day-to-Night Relighting", "showcase_url": "https://v3b.fal.media/files/b/0aa44040/BXGIUDLgWrr4qZ5ZmbaMW_out37_3-3-2.mp4", "showcase_metadata": { "programs": [], "stream_groups": [], "streams": [ { "codec_type": "video", "width": 1280, "height": 720, "r_frame_rate": "24/1", "duration": "6.583333", "nb_frames": "158" }, { "codec_type": "audio", "sample_rate": "32000", "channels": 2, "r_frame_rate": "0/0", "duration": "6.592000", "nb_frames": "207" } ], "format": { "duration": "6.592000" } }, "prompt": "Relighting\n\nChange the lighting in the reference video from daytime to night.", "prompt_sha256": "de0d233e1d97d3cd3095ffbaa98cfbf41bd82d430eb29e10e79263fd31101982", "width": 1344, "height": 768, "fps": 24, "num_frames": 158, "duration_seconds": 6.583333333333333, "source_duration_seconds": 6.583333, "reference_category": "single", "reference_resize_mode": "match", "noise_sha256": { "video": "f6a00b777d4bdfe408156456b7b5baa4f4d45b4c3dcf622f2df90a3d703d54bb", "audio": "6b836dd0d4c4715ad86a56b2f5ea11b5dac16fa5ab067a6f92ab665715288f88" }, "references": [ { "type": "video", "source_url": "https://v3b.fal.media/files/b/0aa44040/emXiHyqHBI1Go4GG7gKxc_3-3-2-2_in1.mp4", "sha256": "b0b0cf00eaa19f2e27d8c3276fa6cd7c542b93c5cc9c2c5580352ace894bcb66", "metadata": { "programs": [], "stream_groups": [], "streams": [ { "codec_type": "video", "width": 1280, "height": 720, "r_frame_rate": "24/1", "duration": "6.041667", "nb_frames": "145" }, { "codec_type": "audio", "sample_rate": "44100", "channels": 2, "r_frame_rate": "0/0", "duration": "6.060000", "nb_frames": "262" } ], "format": { "duration": "6.060000" } }, "url": "references/day_to_night/reference_01.mp4", "label": "Video 1 · 内含 Audio 1" } ], "results": { "base50": { "url": "media/day_to_night/base50.mp4", "poster": "posters/day_to_night/base50.jpg", "metadata_url": "data/day_to_night/base50.json", "generation_seconds": 1606.0486418539658, "context_parallel_degree": 1, "execution_mode": "fsdp_replicated_sample", "independent_samples": 1, "conditioning_cache_hits": 0, "actual_forward_count": 50, "sha256": "f10089280d6909636a1776421f75cb74da951d5a48f3dd4f369e1f5507daa37b" }, "pdd8": { "url": "media/day_to_night/pdd8.mp4", "poster": "posters/day_to_night/pdd8.jpg", "metadata_url": "data/day_to_night/pdd8.json", "generation_seconds": 430.35602481500246, "context_parallel_degree": 1, "execution_mode": "fsdp_replicated_sample", "independent_samples": 1, "conditioning_cache_hits": 0, "actual_forward_count": 8, "sha256": "16382533f3cdd802caab26dc472220db320b6dae68e5be2564ac3f20036ad056" }, "lightx8": { "url": "media/day_to_night/lightx8.mp4", "poster": "posters/day_to_night/lightx8.jpg", "metadata_url": "data/day_to_night/lightx8.json", "generation_seconds": 440.3810706201475, "context_parallel_degree": 1, "execution_mode": "fsdp_replicated_sample", "independent_samples": 1, "conditioning_cache_hits": 0, "actual_forward_count": 8, "sha256": "189cdd6d673e28f6d646022f3b0b159e6e3a251d0fd91c2b785026800932c4a7" }, "vdn8": { "url": "media/day_to_night/vdn8.mp4", "poster": "posters/day_to_night/vdn8.jpg", "metadata_url": "data/day_to_night/vdn8.json", "generation_seconds": 292.7281200401485, "context_parallel_degree": 1, "execution_mode": "fsdp_sample_parallel", "independent_samples": 2, "conditioning_cache_hits": 2, "actual_forward_count": 8, "sha256": "52698e2c025a20a48cbb43e88fafa9ba66e9fb8057676b8edc8a2d41bc7d5f1b" }, "rzgar8": { "url": "media/day_to_night/rzgar8.mp4", "poster": "posters/day_to_night/rzgar8.jpg", "metadata_url": "data/day_to_night/rzgar8.json", "generation_seconds": 252.92025544610806, "context_parallel_degree": 1, "execution_mode": "fsdp_sample_parallel", "independent_samples": 2, "conditioning_cache_hits": 2, "actual_forward_count": 8, "sha256": "dd5e3bd2b09f4292f81fe00e38a2b2c2ff5276e15368b106467e1d2c5f745b41" }, "rkss8": { "url": "media/day_to_night/rkss8.mp4", "poster": "posters/day_to_night/rkss8.jpg", "metadata_url": "data/day_to_night/rkss8.json", "generation_seconds": 972.4119254248217, "context_parallel_degree": 1, "execution_mode": "fsdp_sample_parallel", "independent_samples": 8, "conditioning_cache_hits": 2, "actual_forward_count": 8, "sha256": "ce3fc8092560c3c49282915d2c22016e9ffadd55d9d0d60c64ed232b04a180b0" } }, "prompt_url": "data/day_to_night/prompt.txt" }, { "id": "street_dance", "order": 3, "original_number": 8, "title": "角色替换与街舞迁移", "evaluation_axes": [ "角色外观", "动作时序", "参考分工" ], "seed": 20260917, "source": "fal public H3 showcase (not an open-weight baseline)", "source_url": "https://fal.ai/learn/devs/minimax-h3-prompting-guide", "source_title": "Street Dance Motion Transfer", "showcase_url": "https://v3b.fal.media/files/b/0aa44040/9i6r_L_Iu4c50HEYFNbRX_out30_3-2-2.mp4", "showcase_metadata": { "programs": [], "stream_groups": [], "streams": [ { "codec_type": "video", "width": 1280, "height": 720, "r_frame_rate": "24/1", "duration": "10.125000", "nb_frames": "243" }, { "codec_type": "audio", "sample_rate": "32000", "channels": 2, "r_frame_rate": "0/0", "duration": "10.144000", "nb_frames": "318" } ], "format": { "duration": "10.144000" } }, "prompt": "Use Video 1 as the motion reference for a street-dance performance. Use Images 1 and 2 as the character references.", "prompt_sha256": "88182bc0a185a57141dae69d4cad025a8a736a5aa2c47770cffe85673e0be040", "width": 1344, "height": 768, "fps": 24, "num_frames": 243, "duration_seconds": 10.125, "source_duration_seconds": 10.125, "reference_category": "multi", "reference_resize_mode": "match", "noise_sha256": { "video": "5baa3cbc4969c08f7043270fae90701ced43e2dd33622a7cdd0f72a7c0cd5253", "audio": "72d087b46a7dcc32222fa64f94f1b699cc78db4da181d1b68290ac7ce3d24d86" }, "references": [ { "type": "image", "source_url": "https://v3b.fal.media/files/b/0aa44041/-4dp5kbzdRqinGhtzgS9Q_3-2-2-2_ref1.webp", "sha256": "d5162687c84c2b28fd1bd6d231809afbc66a8b6045b9d630a7dd1bf4cbde33df", "metadata": { "programs": [], "stream_groups": [], "streams": [ { "codec_type": "video", "width": 720, "height": 1264, "r_frame_rate": "25/1" } ], "format": {} }, "url": "references/street_dance/reference_01.webp", "label": "Picture / Image 1" }, { "type": "image", "source_url": "https://v3b.fal.media/files/b/0aa44041/Gas53M7Tuo0s1PYYOQRkE_3-2-2-2_ref2.webp", "sha256": "9824bfaa8b9fae07779e21237f7ae223515b290ff349ff38cb2249e03a42a6ff", "metadata": { "programs": [], "stream_groups": [], "streams": [ { "codec_type": "video", "width": 1280, "height": 717, "r_frame_rate": "25/1" } ], "format": {} }, "url": "references/street_dance/reference_02.webp", "label": "Picture / Image 2" }, { "type": "video", "source_url": "https://v3b.fal.media/files/b/0aa44040/ByMddW2HA-LxjZ8f1X-f3_3-2-2-2_in1.mp4", "sha256": "5ec5085d808cc3cb6d90e32ce9dae1666e9517ecb4e79fc6cb2e3a31ab811c64", "metadata": { "programs": [], "stream_groups": [], "streams": [ { "codec_type": "video", "width": 720, "height": 1280, "r_frame_rate": "30/1", "duration": "9.466667", "nb_frames": "284" }, { "codec_type": "audio", "sample_rate": "44100", "channels": 2, "r_frame_rate": "0/0", "duration": "9.472993", "nb_frames": "409" } ], "format": { "duration": "9.472993" } }, "url": "references/street_dance/reference_03.mp4", "label": "Video 1 · 内含 Audio 1" } ], "results": { "base50": { "url": "media/street_dance/base50.mp4", "poster": "posters/street_dance/base50.jpg", "metadata_url": "data/street_dance/base50.json", "generation_seconds": 3637.029965964146, "context_parallel_degree": 1, "execution_mode": "fsdp_replicated_sample", "independent_samples": 1, "conditioning_cache_hits": 0, "actual_forward_count": 50, "sha256": "38f398ecc8c220858cdec118574ba0e1647a62f153d033579ff2303d205b080e" }, "pdd8": { "url": "media/street_dance/pdd8.mp4", "poster": "posters/street_dance/pdd8.jpg", "metadata_url": "data/street_dance/pdd8.json", "generation_seconds": 581.913629343966, "context_parallel_degree": 1, "execution_mode": "fsdp_sample_parallel", "independent_samples": 8, "conditioning_cache_hits": 2, "actual_forward_count": 8, "sha256": "32accfb2278713934817354b24306f7e5756fc7783a1e6f606fab9f9e0243123" }, "lightx8": { "url": "media/street_dance/lightx8.mp4", "poster": "posters/street_dance/lightx8.jpg", "metadata_url": "data/street_dance/lightx8.json", "generation_seconds": 890.1977515881881, "context_parallel_degree": 1, "execution_mode": "fsdp_replicated_sample", "independent_samples": 1, "conditioning_cache_hits": 0, "actual_forward_count": 8, "sha256": "79bef22feb78de95d2f58bc2ba8638ca485c7aab340503fa9e4e7608f71c5f15" }, "vdn8": { "url": "media/street_dance/vdn8.mp4", "poster": "posters/street_dance/vdn8.jpg", "metadata_url": "data/street_dance/vdn8.json", "generation_seconds": 643.2658445690759, "context_parallel_degree": 1, "execution_mode": "fsdp_sample_parallel", "independent_samples": 8, "conditioning_cache_hits": 2, "actual_forward_count": 8, "sha256": "342d36d746949337d71d6cf86ecb76d029ed8ae5bb45705e263d209c2f370938" }, "rzgar8": { "url": "media/street_dance/rzgar8.mp4", "poster": "posters/street_dance/rzgar8.jpg", "metadata_url": "data/street_dance/rzgar8.json", "generation_seconds": 572.8264107180294, "context_parallel_degree": 1, "execution_mode": "fsdp_sample_parallel", "independent_samples": 8, "conditioning_cache_hits": 2, "actual_forward_count": 8, "sha256": "38a801abfee8d066d9aa4d56fd49ff4d84ea4992af8451237f6bd2b5195d97e5" }, "rkss8": { "url": "media/street_dance/rkss8.mp4", "poster": "posters/street_dance/rkss8.jpg", "metadata_url": "data/street_dance/rkss8.json", "generation_seconds": 975.2969821919687, "context_parallel_degree": 1, "execution_mode": "fsdp_sample_parallel", "independent_samples": 8, "conditioning_cache_hits": 2, "actual_forward_count": 8, "sha256": "7de0c290c56810dedd37c9964686cc868bb18adef75ff3cd65430767cfb9bc93" } }, "prompt_url": "data/street_dance/prompt.txt" }, { "id": "desert_observer", "order": 4, "original_number": 1, "title": "沙漠观测员与望远镜", "evaluation_axes": [ "人物身份", "器械几何", "手部接触" ], "seed": 20260917, "source": "LightX2V public Ref2VA test set", "source_url": "https://github.com/ModelTC/Minimax-H3-Turbo/blob/main/examples/prompts_ref2va_test.json", "source_case_index": 4, "prompt": "subject_definitions:\n is a tan-skinned adult man with close-cropped dark hair, light stubble, a sand-colored field jacket, and a burgundy scarf, as shown in .\n is a vintage brass telescope on a dark tripod, as shown in .\n is a small red-glowing metal lantern on a weathered table, as shown in .\n is a quiet desert observatory at dusk with soft mountain silhouettes, as shown in .\n\nsummary:\n[reference generation] In one continuous 5.1667-second shot inside , notices a distant flash, turns toward , adjusts its focus ring once, and reaches the eyepiece as pulses red.\n\nretention_analysis:\n (appears in [Shot 1]): fully_preserved - Preserve the same adult identity, facial structure, hair, stubble, jacket, scarf, and body proportions.\n (appears in [Shot 1]): fully_preserved - Preserve the same brass tube, black fittings, tripod geometry, scale, and position.\n (appears in [Shot 1]): fully_preserved - Preserve the same metal housing and red light.\n (appears in [Shot 1]): fully_preserved - Preserve the dusk palette, mountain horizon, and sparse desert setting.\n\ndetailed_description:\nVisual style: cinematic naturalism with warm lantern light against a cool violet dusk. One locked medium shot preserves the composition from . The camera stays fixed with no pan, tilt, zoom, or dolly.\n\n[Shot 1, 00:00.000-00:01.300] stands beside as the final dusk light outlines the brass tube and distant mountain ridge. A faint cold flash crosses his eyes from outside frame. He stops breathing for a beat and turns his gaze sharply toward the telescope while holds a steady red glow on the table.\n\n[Shot 1, 00:01.300-00:03.600] He reaches across the brass tube, grips the focus ring, and makes exactly one deliberate adjustment. The mechanism gives a precise metal click. Reflected violet sky slides across the brass surface, his scarf lifts in the desert wind, and flickers once brighter without moving.\n\n[Shot 1, 00:03.600-00:05.166] leans quickly but naturally to the eyepiece, steadies the telescope with his free hand, and peers through it with sudden concentration. The lantern throws a brief red edge across his cheek and telescope fittings. He holds the tense viewing pose as the distant flash fades behind the mountains.\n\noverall_soundscape:\nA faint desert breeze, a soft metal adjustment click, fabric rustle, and a quiet lantern flame.\n\nnon_diegetic_music:\nN/A\n", "prompt_sha256": "b0552f890e3475afb65d322ef0785523e4df088330cee31b0a0a6afa71504417", "width": 1344, "height": 768, "fps": 24, "num_frames": 124, "duration_seconds": 5.166666666666667, "source_duration_seconds": 5.1666666667, "reference_category": "single", "reference_resize_mode": "match", "noise_sha256": { "video": "2fc6ca72960c7a55da99a05475370558d51cbf7e095d4d2d3149d094a75c7d3b", "audio": "93539e5d8f7c8fa64f085483e2ee48b4c3c98947d41906a69941ac7a1cc71445" }, "references": [ { "type": "image", "source_url": "https://raw.githubusercontent.com/ModelTC/Minimax-H3-Turbo/main/examples/ref2va_testset/ref2va_test_4_1.jpg", "sha256": "3b54a682135c5e60c3584df15754c8d54177738686a0778ca89f0a326fe50bbd", "metadata": { "programs": [], "stream_groups": [], "streams": [ { "codec_type": "video", "width": 1402, "height": 1122, "r_frame_rate": "25/1", "duration": "0.040000" } ], "format": { "duration": "0.040000" } }, "url": "references/desert_observer/reference_01.jpg", "label": "Picture / Image 1" } ], "results": { "base50": { "url": "media/desert_observer/base50.mp4", "poster": "posters/desert_observer/base50.jpg", "metadata_url": "data/desert_observer/base50.json", "generation_seconds": 1854.7577296537347, "context_parallel_degree": 1, "execution_mode": "fsdp_sample_parallel", "independent_samples": 7, "conditioning_cache_hits": 0, "actual_forward_count": 50, "sha256": "ffbf4cbf7dea8a2d707230ed7d2ebd267040048f350555b3bbaabf60e2c01be7" }, "pdd8": { "url": "media/desert_observer/pdd8.mp4", "poster": "posters/desert_observer/pdd8.jpg", "metadata_url": "data/desert_observer/pdd8.json", "generation_seconds": 578.5816156761721, "context_parallel_degree": 1, "execution_mode": "fsdp_sample_parallel", "independent_samples": 8, "conditioning_cache_hits": 2, "actual_forward_count": 8, "sha256": "fce977e36babb996f20904ff747d379cea882c8ee6ad8ed3bc28de7fae7585d5" }, "lightx8": { "url": "media/desert_observer/lightx8.mp4", "poster": "posters/desert_observer/lightx8.jpg", "metadata_url": "data/desert_observer/lightx8.json", "generation_seconds": 94.16709342109971, "context_parallel_degree": 1, "execution_mode": "fsdp_replicated_sample", "independent_samples": 1, "conditioning_cache_hits": 0, "actual_forward_count": 8, "sha256": "8b096cce8e094eede4dae8fe015cc1394b5cdd05cacfdb72b6d67c49893c2b45" }, "vdn8": { "url": "media/desert_observer/vdn8.mp4", "poster": "posters/desert_observer/vdn8.jpg", "metadata_url": "data/desert_observer/vdn8.json", "generation_seconds": 640.1438372218981, "context_parallel_degree": 1, "execution_mode": "fsdp_sample_parallel", "independent_samples": 8, "conditioning_cache_hits": 2, "actual_forward_count": 8, "sha256": "45320e75ff2582af7e74ea5f1d30344a5e552d1c33fac7bb9320d01e30951c81" }, "rzgar8": { "url": "media/desert_observer/rzgar8.mp4", "poster": "posters/desert_observer/rzgar8.jpg", "metadata_url": "data/desert_observer/rzgar8.json", "generation_seconds": 568.8851783860009, "context_parallel_degree": 1, "execution_mode": "fsdp_sample_parallel", "independent_samples": 8, "conditioning_cache_hits": 2, "actual_forward_count": 8, "sha256": "16cc137feb590424c7ea317dc12c2f29efc9225df8737b967cf74f265d7f7a40" }, "rkss8": { "url": "media/desert_observer/rkss8.mp4", "poster": "posters/desert_observer/rkss8.jpg", "metadata_url": "data/desert_observer/rkss8.json", "generation_seconds": 200.53608646499924, "context_parallel_degree": 1, "execution_mode": "fsdp_sample_parallel", "independent_samples": 2, "conditioning_cache_hits": 2, "actual_forward_count": 8, "sha256": "861c79a91c5875b149f207ab25b9a5423ef173850dfcac2b260aeb2c11b997e5" } }, "prompt_url": "data/desert_observer/prompt.txt" }, { "id": "voice_lamb", "order": 5, "original_number": 10, "title": "抱羊男子按参考音色说话", "evaluation_axes": [ "音色参考", "台词与口型", "源场景保持" ], "seed": 20260917, "source": "MiniMax official reproducible Ref2VA request", "source_url": "https://raw.githubusercontent.com/MiniMax-AI/MiniMax-H3/main/scripts/readme/reproducible-768p-ref2va-request.sh", "prompt": "subject_definitions:\n is the young man with short wavy blonde hair, wearing a bright pink suit jacket, matching pink trousers, an unbuttoned white shirt, and silver rings, holding a small black lamb in his arms in