Add diffusers format weights

README.md

@@ -3,7 +3,7 @@ pipeline_tag: image-text-to-video
 license: other
 license_name: minimax-h3-community-license-agreement
 license_link: LICENSE
-library_name: minimax-h3
+library_name: diffusers
 tags:
   - text-to-video
   - image-to-video
@@ -18,7 +18,6 @@ tags:
   - multimodal
   - synchronized-audio-video
   - reference-to-audio-video
-  - diffusers
 ---
 
 <div align="center">
@@ -29,30 +28,16 @@ tags:
   <a href="https://hailuoai.video" target="_blank"><img src="https://img.shields.io/badge/Hailuo%20AI-FF6C37?logo=minimax&logoColor=white" alt="Hailuo AI"></a>
   <a href="https://platform.minimax.io/docs/guides/text-generation" target="_blank"><img src="https://img.shields.io/badge/API-FF6C37?logo=minimax&logoColor=white" alt="API"></a>
   <a href="https://www.minimax.io" target="_blank"><img src="https://img.shields.io/badge/MiniMax%20Website-FF6C37?logo=minimax&logoColor=white" alt="MiniMax Website"></a>
-  <a href="https://github.com/MiniMax-AI/MiniMax-H3" target="_blank"><img src="https://img.shields.io/badge/GitHub-181717?logo=github&logoColor=white" alt="GitHub"></a>
-  <a href="https://huggingface.co/MiniMaxAI/MiniMax-H3" target="_blank"><img src="https://img.shields.io/badge/Hugging%20Face-FFD21E?logo=huggingface&logoColor=black" alt="Hugging Face"></a>
   <br>
   <a href="https://modelscope.cn/organization/minimax" target="_blank" rel="noopener noreferrer"><img alt="ModelScope MiniMax AI" src="https://img.shields.io/badge/ModelScope-MiniMax%20AI-white?labelColor=%23EF3D5D"></a>
   <a href="https://platform.minimaxi.com/docs/faq/contact-us" target="_blank"><img src="https://img.shields.io/badge/WeChat-07C160?logo=wechat&logoColor=white" alt="WeChat"></a>
   <a href="https://discord.com/invite/dbMxutw7tP" target="_blank"><img src="https://img.shields.io/badge/Discord-5865F2?logo=discord&logoColor=white" alt="Discord"></a>
-  <a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE"><img src="https://img.shields.io/badge/LICENSE-4CAF50?logo=creativecommons&logoColor=white" alt="LICENSE"></a>
+  <a href="https://huggingface.co/MiniMaxAI" target="_blank"><img src="https://img.shields.io/badge/Hugging%20Face-FFD21E?logo=huggingface&logoColor=black" alt="Hugging Face"></a>
+  <a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE" target="_blank"><img src="https://img.shields.io/badge/LICENSE-4CAF50?logo=creativecommons&logoColor=white" alt="LICENSE"></a>
 </p>
 
-
 # MiniMax H3
 
-## News
-Offical skills to improve prompt writing: [skills on github](https://github.com/MiniMax-AI/MiniMax-H3/tree/main/skills)
-
-## 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/tools/minimax-h3) \| 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.
 
@@ -72,7 +57,7 @@ H3 supports the following input and output specifications:
 | Model Variant | Input Mode | Specifications |
 |---|---|---|
 | H3-Base-FL2VA | First-and-last-frame mode | Supports zero, one, or two input images. <br><br>- No image input: Text-to-video mode <br>- One image input: First-frame-to-video or last-frame-to-video generation <br>- Two image inputs: First-and-last-frame-to-video generation |
-| H3-Base-Ref2VA | Omni-reference mode | Supports multi-modal reference inputs: <br><br>- **Images:** ≤ 9 images <br>- **Videos:** ≤ 3 clips; each clip must be 2–15 seconds long; total duration ≤ 15 seconds <br>- **Audio:** ≤ 3 clips; each clip must be 2–15 seconds long; total duration ≤ 15 seconds <br>- **Mixed inputs:** Maximum number of files across all input types is 12 |
+| H3-Base-Ref2VA | Omni-reference mode | Supports multi-modal reference inputs: <br><br>- **Images:** ≤ 9 images <br>- **Videos:** ≤ 3 clips; each clip must be 2–15 seconds long; total duration ≤ 15 seconds <br>- **Audio:** ≤ 3 clips; audio must be accompanied by image or video input and cannot be used as the sole input; each clip must be 2–15 seconds long; total duration ≤ 15 seconds <br>- **Mixed inputs:** Maximum number of files across all input types is 12 |
 
 ![Image](assets/overview.png)
 
@@ -81,6 +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
@@ -193,27 +192,19 @@ Each checkpoint is distributed as a self\-contained Hugging Face\-style reposito
 └── audio_vae/
 ```
 
-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 public entry. The task-family-specific diffusers indexes remain under `FL2VA/model_index.json` and `Ref2VA/model_index.json`.
+Download the model:
 
 ```bash
-# Original checkpoint, both task families (SGLang, vLLM):
-hf download MiniMaxAI/MiniMax-H3 --include "model_index.json" "FL2VA/*" "Ref2VA/*" --local-dir MiniMax-H3
-
-# Or a single task family:
-hf download MiniMaxAI/MiniMax-H3 --include "model_index.json" "FL2VA/*" --local-dir MiniMax-H3
+hf download MiniMaxAI/MiniMax-H3 --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://huggingface.co/docs/diffusers/main/en/api/pipelines/minimax_h3) for loading recipes.
-
 We recommend the following inference frameworks to serve the model:
 
 - [SGLang](https://docs.sglang.io/) \- see [cookbook](https://docs.sglang.io/cookbook/diffusion/MiniMax/MiniMax-H3) 
 
 - [vLLM](https://github.com/vllm-project/vllm) \- see [vllm recipes](https://recipes.vllm.ai/MiniMaxAI/MiniMax-H3)
 
-- [diffusers](https://github.com/huggingface/diffusers) \- see [diffusers docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/minimax_h3)
+- [diffusers](https://github.com/huggingface/diffusers) \- see [diffusers docs](https://huggingface.co/docs/diffusers/en/api/models/autoencoderkl_minimax_h3)
 
 - [ComfyUI](https://github.com/Comfy-Org/ComfyUI) \- see  [Comfy tutorial](https://docs.comfy.org/tutorials/video/minimax/minimax-h3); use [R2V template](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/video_minimax_h3_r2v.json) / [T2V template](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/video_minimax_h3_t2v.json)
 
@@ -278,11 +269,8 @@ TOKEN="<token>"
 
 MiniMax platform:
 
-API docs:
-- Create H3-2K: use /video-generation-v2-create [EN-docs](https://platform.minimax.io/docs/api-reference/video-generation-v2-create), [CN-docs](https://platform.minimaxi.com/docs/api-reference/video-generation-v2-create)
-- H3-Context-IR：use /video-generation-v2-h3-context-ir [EN-docs](https://platform.minimax.io/docs/api-reference/video-generation-v2-h3-context-ir), [CN-docs](https://platform.minimaxi.com/docs/api-reference/video-generation-v2-h3-context-ir)
-- H3-Regenerate-2K：use /video-generation-v2-regeneration [EN-docs](https://platform.minimax.io/docs/api-reference/video-generation-v2-regeneration), [CN-docs](https://platform.minimaxi.com/docs/api-reference/video-generation-v2-regeneration)
-
+- CN: https://platform.minimaxi.com
+- Global: https://platform.minimax.io
 
 The examples below encode local H3\-Base output files as Base64 Data URLs\. For production use, uploading the video to a publicly accessible URL and passing that URL as `base_video` is recommended\.
 
@@ -411,13 +399,11 @@ For each case below, we provide reference outputs at both 2K and 768p generated
 
 [VIDEO\_PROMPT\_WRITING\_GUIDE\_ref\_en\.md](docs/VIDEO_PROMPT_WRITING_GUIDE_ref_en.md)
 
-skills to improve prompt: https://github.com/MiniMax-AI/MiniMax-H3/tree/main/skills
+
 
 ## License
 
-- MiniMax H3 is released under the [MiniMax H3 Community License Agreement](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE).
-- [Q&A about the License](docs/QA-about-License.md)
-- [Application form(only for USA/EU/UK/South Korea)](https://platform.minimax.io/h3-license)
+MiniMax H3 is released under the [MiniMax H3 Community License Agreement](LICENSE).  [Q&A about License](docs/QA-about-License.md)
 
 ## Contact Us
 

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

docs/QA-about-License.md

@@ -45,7 +45,7 @@ Yes.
 
 Organizations in these regions can apply for a formal license. After reviewing the deployment scenario and confirming that appropriate compliance controls and safeguards are implemented, MiniMax may authorize usage.
 
-[Application form](https://platform.minimax.io/h3-license)
+[Application form](https://vrfi1sk8a0.feishu.cn/share/base/form/shrcnD9XM1zYI9VFJxTEbt0d19g)
 
 Through authorized deployments, MiniMax can ensure that MiniMax-H3 is used responsibly while meeting local legal and regulatory requirements.
 

model_index.json

@@ -1,131 +0,0 @@
-{
-  "_class_name": "MiniMaxH3ModularPipeline",
-  "_diffusers_version": "0.36.0.dev0",
-  "_blocks_class_name": "MiniMaxH3Blocks",
-  "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
-    }
-  ]
-}