Duplicate from WarmBloodAban/Minimax-h3_Singularity

Co-authored-by: AIGC Singularity <WarmBloodAban@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,42 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+video/1.mp4 filter=lfs diff=lfs merge=lfs -text
+video/2.mp4 filter=lfs diff=lfs merge=lfs -text
+video/3.mp4 filter=lfs diff=lfs merge=lfs -text
+video/AIGCTYD2_00001_p84-audio_ganvc_1788634594[[:space:]](1).mp4 filter=lfs diff=lfs merge=lfs -text
+video/AIGCTYD2_00001_p85-audio_jrski_1788643962[[:space:]](1).mp4 filter=lfs diff=lfs merge=lfs -text
+video/AIGCTYD2_00003_p82-audio_aqukl_1788646377[[:space:]](29).mp4 filter=lfs diff=lfs merge=lfs -text
+video/AIGCTYD2_00010_p87-audio_alipa_1788652671.mp4 filter=lfs diff=lfs merge=lfs -text

Minimax-h3_Singularity_ref2va_Pruned_v1.3_int8.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:412a7b126595a958964193f3b42513d7cf2df4196ef04223a0f05e3622949cce
+size 20967647456

Minimax-h3_Singularity_ref2va_v1.3_int8.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:551915097b8727537a82f3a2c5acec965165ec84e780b3e9a5f28ce867fddf08
+size 34004507622

README.md

@@ -0,0 +1,98 @@
+---
+license: apache-2.0
+language:
+- en
+- zh
+pipeline_tag: image-to-video
+tags:
+- video-generation
+- text-to-video
+- image-to-video
+- video-to-video
+- reference-to-video
+- minimax-h3
+- comfyui
+- fine-tuned
+- hdr
+- singularity
+---
+
+# Minimax-h3_Singularity
+
+<p align="center">
+  <a href="https://www.runninghub.ai/post/2096339589492432897/?inviteCode=rh-v1559">
+    <img src="https://img.shields.io/badge/🚀_Online_Demo-RunningHub-blue.svg" alt="Online Demo">
+  </a>
+  <a href="https://youtube.com/@AIGC-Singularity">
+    <img src="https://img.shields.io/badge/YouTube-AIGC--Singularity-red.svg" alt="YouTube">
+  </a>
+  <a href="https://space.bilibili.com">
+    <img src="https://img.shields.io/badge/Bilibili-AIGC--Singularity_Space-00a1d6.svg" alt="Bilibili">
+  </a>
+</p>
+
+## 📖 Model Overview
+
+**Minimax-h3_Singularity** is a comprehensive fine-tuned fusion model specialized in enhancing the capabilities of **MiniMax-H3**. Designed as a versatile **multimodal video generation model**, it natively supports **Text-to-Video (T2V)**, **Image-to-Video (I2V)**, **Reference-to-Video (Ref2V)**, and **Video-to-Video (V2V)** workflows within **ComfyUI**.
+
+Built upon a strategic fusion of key checkpoints (including `ref`, `fl`, `b25-49`, etc.), this model underwent deep high-step fine-tuning. To preserve the original model's foundational strengths and broad generalization while solving artifacts introduced by high-step training, we spent **3 full days on precise model pruning and weight optimization**. The result is a clean, sharp, and highly dynamic video generation model.
+
+---
+
+## ✨ Key Improvements & Features
+
+* 🎬 **HDR Image Quality & Blur Reduction**: Fine-tuned on high-dynamic-range (HDR) video datasets to significantly enhance visual clarity and eliminate motion blur during high-speed action.
+* 👤 **Distant Face Restoration**: Drastically reduces facial distortion, blurriness, and collapsing in medium-to-long shots.
+* 🎨 **Clean & De-Oiled Aesthetic**: Removes heavy, unnatural skin shine and glossy textures, rendering natural lighting and photorealistic materials.
+* ⚔️ **Enhanced Dynamic Motion**: Boosts motion fluidity and physical impact, excels in complex action sequences such as **sword fighting and martial arts/melee combat**.
+* 🌌 **VFX & Fantasy Effects**: Specifically optimized for fantasy spellcasting, particle aura, and magical combat visual effects.
+* 🎭 **Expressive Facial Dynamics**: Captures subtle facial expressions and emotional nuances more vividly.
+* 📹 **Cinematography & Camera Control**: Strengthens responsiveness to camera movements (pan, tilt, zoom, tracking shots) for cinematic storytelling.
+* 🛡️ **Full Base Capability Retention**: 100% preserves MiniMax-H3's original prompt adherence, style adaptability, and base multimodal generation strength.
+
+---
+
+## 🎬 Showcase
+
+<video src="https://huggingface.co/WarmBloodAban/Minimax-h3_Singularity/resolve/main/video/1.mp4" controls autoplay loop muted width="20%"></video>
+<video src="https://huggingface.co/WarmBloodAban/Minimax-h3_Singularity/resolve/main/video/3.mp4" controls autoplay loop muted width="20%"></video>
+<video src="https://huggingface.co/WarmBloodAban/Minimax-h3_Singularity/resolve/main/video/AIGCTYD2_00001_p84-audio_ganvc_1788634594%20(1).mp4" controls autoplay loop muted width="20%"></video>
+<video src="https://huggingface.co/WarmBloodAban/Minimax-h3_Singularity/resolve/main/video/AIGCTYD2_00010_p87-audio_alipa_1788652671.mp4" controls autoplay loop muted width="20%"></video>
+
+---
+
+## 💡 Usage Guide
+
+### Multimodal Pipeline Support
+This model is fully compatible with **ComfyUI** and supports:
+* **Text-to-Video (T2V)**
+* **Image-to-Video (I2V)**
+* **Reference-to-Video (Ref2V)**
+* **Video-to-Video (V2V)**
+
+### 🚀 Recommended Acceleration LoRA
+For high-speed generation with minimal quality loss, we strongly recommend pairing with:
+* **`minimax_h3_ref2v_turbo_4step_v0.1`** (Enables 4-step fast inference)
+
+### 🌐 Online Interactive Demo
+Test the model directly in your browser without local GPU setup:
+👉 [**Try it on RunningHub Workflows**](https://www.runninghub.ai/post/2096339589492432897/?inviteCode=rh-v1559)
+
+---
+
+## 🙏 Acknowledgements
+
+Special thanks to the **MiniMax** open-source team for creating and releasing the powerful `MiniMax-H3` multimodal video model, providing a solid foundation for the open-source community! 🤝
+
+---
+
+## 🤝 Community & Commercial Inquiries
+
+Feel free to connect for tutorials, community discussions, workflow sharing, or commercial collaborations:
+
+* **YouTube Channel**: [AIGC-Singularity](https://youtube.com/@AIGC-Singularity)
+* **Bilibili Channel**: AIGC-Singularity Space
+* **QQ Group 1**: `1058747239` (Request to join)
+* **QQ Group 2**: `1072010342` (Request to join)
+* **Business Inquiries (WeChat)**: `aigctyd`
+* **Email**: `a592991299@gmail.com`

video/1.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48e1856ff43c796da2609a3f05ee6b09567bc8e537cbd8204b13bb21b36496a0
+size 10942666

video/2.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:005c07600e9aefd3cbb40e71f89b84d07a5a7c9c8cc039236ea92c118af972cb
+size 8539965

video/3.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4569d372d41402d17c2fa127dc46104b491a690023567a023432ab92a42f625b
+size 12322575

video/AIGCTYD2_00001_p84-audio_ganvc_1788634594 (1).mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fa0174b2f055c24f6103fe7815b9236b2f9785ebb6c1e6a695001c3ef32e3e7
+size 7177840

video/AIGCTYD2_00001_p85-audio_jrski_1788643962 (1).mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da1f0ac234db8d8e38ccd659323d7a1b9309590c18d6f82046c3133a94b718e
+size 12167506

video/AIGCTYD2_00003_p82-audio_aqukl_1788646377 (29).mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff231c3b0bc4d29a385747f0ab1deb96b283232cf7379d9dc1bd4d965b8ba26e
+size 8319209

video/AIGCTYD2_00010_p87-audio_alipa_1788652671.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe63d409463388a58ad8d0b4ea1ed19c0d777933eb884f098c7f87425a462e89
+size 4586206