VDN is a new attention system for MiniMax H3. It makes video generation much more efficient by keeping normal attention where it matters for nearby frames, while using a much cheaper linear attention mechanism for long-range information across the video.INT8 ConvRot VDN stage checkpoint prepared for ComfyUI-VDN-H3-24GB node to use on custom PCs with 24Gb GPU.In simple words, this adapter (model) and my ComfyUI node allow you to generate videos in 8 steps without turbo LORAs and get a quality close to the quality of the original model in 20 steps.If you ask is it faster? I will definitely say yes, it is faster than generating 20 steps on the original model. But if you compare the generation time with generation using turbo LORAs, it will be a little slower, but the waiting time is worth it if you need quality. You can see the test results below.How to use it:download archive "stage-dmd-step-250-int8_convrot_comfyui" unzip it and put it in a directory ComfyUI/models/vdn/ full way should be ComfyUI/models/vdn/stage-dmd-step-250-int8_convrot_comfyui/. !!!do not change the names of the models!!!Same model on HF: <a target="_blank" rel="ugc" href="https://huggingface.co/speach1sdef178/VDN-H3-INT8-ConvRot-ComfyUI">speach1sdef178/VDN-H3-INT8-ConvRot-ComfyUI · Hugging Face</a>The final local structure must be:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/9ecdcf96-efdb-4d10-9c30-d774b21c8e6d/original=true/9ecdcf96-efdb-4d10-9c30-d774b21c8e6d.jpeg" /><h3 id="required-comfyui-node-https:github.comspeach1sdef178comfyui-vdn-h3-24gb">Required ComfyUI node <a target="_blank" rel="ugc" href="https://github.com/Speach1sdef178/ComfyUI-VDN-H3-24GB">https://github.com/Speach1sdef178/ComfyUI-VDN-H3-24GB</a></h3><h3 id="the-node-has-been-added-to-the-comfyui-manager">The node has been added to the ComfyUI Manager</h3>24 GB-oriented MiniMax-H3 VDN runtime for ComfyUI. Version 1.1.0 keeps the validated v49 AutoMemory/AutoLongCache policy and adds three narrowly scoped correctness and memory-safety fixes tested on an RTX 3090 24 GB.Example WF in the attached files<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/31943a4b-95ae-425a-a806-e16d2fc4a6ab/original=true/31943a4b-95ae-425a-a806-e16d2fc4a6ab.jpeg" />License: This model is a derivative of MiniMax H3 and is subject to the MiniMax H3 Community License Agreement.

INT8 ConvRot VDN H3-24GB

VDN is a new attention system for MiniMax H3. It makes video generation much more efficient by keeping normal attention where it matters for nearby frames, while using a much cheaper linear attention mechanism for long-range information across the video.INT8 ConvRot VDN stage checkpoint prepared for ComfyUI-VDN-H3-24GB node to use on custom PCs with 24Gb GPU.How to use it:download archive "stage-dmd-step-250-int8_convrot_comfyui" unzip it and put it in a directory ComfyUI/models/vdn/ full way should be ComfyUI/models/vdn/stage-dmd-step-250-int8_convrot_comfyui/. !!!do not change the names of the models!!!same model on HF: <a target="_blank" rel="ugc" href="https://huggingface.co/speach1sdef178/VDN-H3-INT8-ConvRot-ComfyUI">speach1sdef178/VDN-H3-INT8-ConvRot-ComfyUI · Hugging Face</a>The final local structure must be:ComfyUI/└─ models/└─ vdn/└─ stage-dmd-step-250-int8_convrot_comfyui/├─ model_spec.json├─ linear_branch/│ └─ model_int8_convrot_comfyui.safetensors└─ adapters/├─ default/│ ├─ adapter_config.json│ └─ adapter_model.safetensors└─ turbo/├─ adapter_config.json└─ adapter_model.safetensorsRequired ComfyUI node <a target="_blank" rel="ugc" href="https://github.com/Speach1sdef178/ComfyUI-VDN-H3-24GB">https://github.com/Speach1sdef178/ComfyUI-VDN-H3-24GB</a>24 GB-oriented MiniMax-H3 VDN runtime for ComfyUI. Version 1.1.0 keeps the validated v49 AutoMemory/AutoLongCache policy and adds three narrowly scoped correctness and memory-safety fixes tested on an RTX 3090 24 GB.Example WF in the attached filesLicense: This model is a derivative of MiniMax H3 and is subject to the MiniMax H3 Community License Agreement.

Files with SHA256: 000881e62023463013fb2d6a104a315609f09d009122cdc4c20b7aa281bcad86