Scope the download command to the original checkpoint folders

README.md

@@ -38,16 +38,6 @@ tags:
 
 # MiniMax H3
 
-## Online API
-Use MiniMax\-H3 directly via API\. 
-- Global: [platform\.minimax\.io](https://platform.minimax.io/docs/api-reference/video-generation-v2-create) \| CN: [platform\.minimaxi\.com](https://platform.minimaxi.com/docs/api-reference/video-generation-v2-create)
-
-## Online App
-Use MiniMax\-H3 directly via App\.
-- WebApp Global: [hailuoai\.video](https://hailuoai.video) \| CN: [hailuoai\.com](https://hailuoai.com/)
-- Desktop Global: [hub\.minimax\.io](https://hub.minimax.io/) \| CN: [hub\.minimaxi\.com](https://hub.minimaxi.com/)
-
-
 ## System Overview
 MiniMax H3 is a general-purpose, omni-modal generative system. It supports unified understanding of multimodal contexts composed of text, images, video, and audio, and can generate video with native stereo audio at resolutions up to 2K and durations of up to 15 seconds. Thanks to its task-generalization-oriented system design, H3 already possesses broad multimodal context understanding and generation capabilities at the pre-training stage, enabling outstanding performance in following complex multimodal instructions.
 
@@ -76,6 +66,20 @@ The complete H3 system consists of the following three modules:
 - H3-Base: Generates audio and video based on the H3-Context-IR output, producing results at 768p resolution.
 - H3-Regenerate-2K: Feeds the 768p result together with the original context back into H3 to regenerate the output at 2K resolution. This process leverages both H3’s powerful generative capabilities and the rich information contained in the original context, enabling it to produce high-resolution outputs with more accurate details and greater visual fidelity.
 
+## Online API
+
+Use MiniMax\-H3 directly via API\. 
+
+- Global: [platform\.minimax\.io](https://platform.minimax.io/docs/api-reference/video-generation-v2-create) \| CN: [platform\.minimaxi\.com](https://platform.minimaxi.com/docs/api-reference/video-generation-v2-create)
+
+## Online App
+
+Use MiniMax\-H3 directly via App\.
+
+- WebApp Global: [hailuoai\.video](https://hailuoai.video) \| CN: [hailuoai\.com](https://hailuoai.com/)
+
+- Desktop Global: [hub\.minimax\.io](https://hub.minimax.io/) \| CN: [hub\.minimaxi\.com](https://hub.minimaxi.com/)
+
 ## Model Architecture
 
 ### H3\-Context\-IR
@@ -190,14 +194,12 @@ Each checkpoint is distributed as a self\-contained Hugging Face\-style reposito
 
 Download the model. The repository hosts the original checkpoint (`FL2VA/`, `Ref2VA/`) and the diffusers format side by side, so scope the download to what your framework needs:
 
-`model_index.json` is the repository-level modular index. The task-family-specific diffusers indexes remain under `FL2VA/model_index.json` and `Ref2VA/model_index.json`.
-
 ```bash
 # Original checkpoint, both task families (SGLang, vLLM):
-hf download MiniMaxAI/MiniMax-H3 --include "model_index.json" "modular_model_index.json" "FL2VA/*" "Ref2VA/*" --local-dir MiniMax-H3
+hf download MiniMaxAI/MiniMax-H3 --include "FL2VA/*" "Ref2VA/*" --local-dir MiniMax-H3
 
 # Or a single task family:
-hf download MiniMaxAI/MiniMax-H3 --include "model_index.json" "modular_model_index.json" "FL2VA/*" --local-dir MiniMax-H3
+hf download MiniMaxAI/MiniMax-H3 --include "FL2VA/*" --local-dir MiniMax-H3
 ```
 
 diffusers users do not need a manual download: `ModularPipeline.from_pretrained("MiniMaxAI/MiniMax-H3")` fetches exactly the components it needs. See the [diffusers documentation](https://github.com/huggingface/diffusers/blob/minimax-h3/docs/source/en/api/pipelines/minimax_h3.md) for loading recipes.

assets/action-reference.mov

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:116e0f08a399834e7ffc3472d036659b33250f4ba4f0b7e63f17ec07cb58e4dc
+size 31446151

assets/character-replacement-action-reference.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:796c264126110d87992dcb54213ac0697920cb4ddf3d5a06aa36069386fc4fa1
+size 8223683

assets/fashion-glasses-ad.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a11e6b0095dd7766b724bb886edf4d7d9930af44da6839ee195269ac4fc60ba4
+size 10938085

assets/fl2va-clay-fox.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4604b0838b736ecaa209c978f880bfacbb3a0fc82a8a0517c1f5aa16454b50ef
+size 10931936

assets/h3-cinematic-shot.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:436defc81cfa7d53aef423f368be82ead20056088087e0be308b6e3865e8fb81
+size 4361547

assets/h3-suspense-title.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90ebbd7edc71c9a0151c3064126acd2dbb5b7cba58ce459e223e29f2c04f9186
+size 16809220

assets/robot-arm-red-cube.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a751e6100dbf6502a99a2adc0b12171304ca7b17eecea70e2ed035a73ea692c
+size 2259732

assets/t2va-768p-demo.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d66903241362e224085cc93f7a5e70fba6ab378d0ac6ff6af83acf2559849a42
+size 1637373

model_index.json

@@ -1,139 +0,0 @@
-{
-  "_class_name": "MiniMaxH3ModularPipeline",
-  "_diffusers_version": "0.36.0.dev0",
-  "_blocks_class_name": "MiniMaxH3Blocks",
-  "_minimax_h3": {
-    "schema_version": 1,
-    "index_scope": "repository",
-    "task_family_indexes": {
-      "fl2va": "FL2VA/model_index.json",
-      "ref2va": "Ref2VA/model_index.json"
-    }
-  },
-  "text_encoder": [
-    "transformers",
-    "Qwen3VLForConditionalGeneration",
-    {
-      "type_hint": [
-        "transformers",
-        "Qwen3VLForConditionalGeneration"
-      ],
-      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
-      "subfolder": "text_encoder",
-      "variant": null,
-      "revision": null
-    }
-  ],
-  "tokenizer": [
-    "transformers",
-    "Qwen2TokenizerFast",
-    {
-      "type_hint": [
-        "transformers",
-        "Qwen2TokenizerFast"
-      ],
-      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
-      "subfolder": "tokenizer",
-      "variant": null,
-      "revision": null
-    }
-  ],
-  "processor": [
-    "transformers",
-    "Qwen3VLProcessor",
-    {
-      "type_hint": [
-        "transformers",
-        "Qwen3VLProcessor"
-      ],
-      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
-      "subfolder": "processor",
-      "variant": null,
-      "revision": null
-    }
-  ],
-  "vae": [
-    "diffusers",
-    "AutoencoderKLMiniMaxH3",
-    {
-      "type_hint": [
-        "diffusers",
-        "AutoencoderKLMiniMaxH3"
-      ],
-      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
-      "subfolder": "vae",
-      "variant": null,
-      "revision": null
-    }
-  ],
-  "audio_vae": [
-    "diffusers",
-    "AutoencoderKLMiniMaxH3Audio",
-    {
-      "type_hint": [
-        "diffusers",
-        "AutoencoderKLMiniMaxH3Audio"
-      ],
-      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
-      "subfolder": "audio_vae",
-      "variant": null,
-      "revision": null
-    }
-  ],
-  "transformer": [
-    "diffusers",
-    "MiniMaxH3Transformer3DModel",
-    {
-      "type_hint": [
-        "diffusers",
-        "MiniMaxH3Transformer3DModel"
-      ],
-      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
-      "subfolder": "transformer",
-      "variant": null,
-      "revision": null
-    }
-  ],
-  "transformer_ref": [
-    "diffusers",
-    "MiniMaxH3Transformer3DModel",
-    {
-      "type_hint": [
-        "diffusers",
-        "MiniMaxH3Transformer3DModel"
-      ],
-      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
-      "subfolder": "transformer_ref",
-      "variant": null,
-      "revision": null
-    }
-  ],
-  "scheduler": [
-    "diffusers",
-    "MiniMaxH3Scheduler",
-    {
-      "type_hint": [
-        "diffusers",
-        "MiniMaxH3Scheduler"
-      ],
-      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
-      "subfolder": "scheduler",
-      "variant": null,
-      "revision": null
-    }
-  ],
-  "audio_scheduler": [
-    "diffusers",
-    "MiniMaxH3Scheduler",
-    {
-      "type_hint": [
-        "diffusers",
-        "MiniMaxH3Scheduler"
-      ],
-      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
-      "subfolder": "audio_scheduler",
-      "variant": null,
-      "revision": null
-    }
-  ]
-}