<h1 id="important-attribution-and-credits">Important Attribution and Credits</h1>Anima LiquidMix is a derivative experimental model-merging project built on top of the existing Anima ecosystem.This project does not claim authorship of the original Anima architecture, the Anima 3.8B / 52-block architecture, the Qwen3.5 conditioning approach, Expanded Conditioning, or Semantic Connector v2.The underlying Anima model architecture and Anima 3.8B development originate from the original Anima projects:<ul><li>Anima Expanded 3.8B <a target="_blank" rel="ugc" href="https://civarchive.com/models/2910974/anima-expanded-38b">https://civarchive.com/models/2910974/anima-expanded-38b</a></li><li>Anima 3.8B <a target="_blank" rel="ugc" href="https://civarchive.com/models/2880480/anima-38b">https://civarchive.com/models/2880480/anima-38b</a></li><li>Anima 3.8B repository by lylogummy <a target="_blank" rel="ugc" href="https://huggingface.co/lylogummy/Anima-3.8B">https://huggingface.co/lylogummy/Anima-3.8B</a></li></ul>The current ComfyUI implementation used by this workflow, including the Anima 3.8B V2 loading path and Semantic Connector v2 inference support, is provided by:<ul><li>GumGum10 / comfyui-anima-3-8B <a target="_blank" rel="ugc" href="https://github.com/GumGum10/comfyui-anima-3-8B">https://github.com/GumGum10/comfyui-anima-3-8B</a></li></ul>LiquidMix only adapts its experimental merged weights to work with this existing ecosystem.<hr /><h1 id="semantic-connector-v2-v2-bundle-compatibility">Semantic Connector v2 / V2 Bundle Compatibility</h1><code>Anima3.8B_LiquidMix_v4.03D.safetensors</code> is distributed in a format compatible with the current Anima 3.8B V2 bundle loading path.The checkpoint includes the LiquidMix Anima 3.8B / 52-block diffusion weights together with the Semantic Connector v2 bundle data required by the current V2 loader.It can therefore be loaded directly with:<code>Anima38BV2Loader</code>from:<code>GumGum10/comfyui-anima-3-8B</code>A separate LiquidMix-specific <code>Anima38BV2EmbeddedLoader</code> compatibility patch is no longer required.<hr /><h1 id="current-anima-3.8b-loader">Current Anima 3.8B Loader</h1>The current LiquidMix workflow uses the nodes provided directly by:GumGum10 / comfyui-anima-3-8B<a target="_blank" rel="ugc" href="https://github.com/GumGum10/comfyui-anima-3-8B">https://github.com/GumGum10/comfyui-anima-3-8B</a>Relevant nodes include:<code>Anima38BV2Loader</code><code>Anima38BV2Prompt</code><code>AnimaQwen35Loader</code><code>AnimaQwen35UnifiedPrompt</code>The current repository includes the Semantic Connector v2 inference implementation required by the V2 workflow.For the current LiquidMix V2 Bundle workflow, do not install the old LiquidMix-specific <code>Anima38BV2EmbeddedLoader</code>.<hr /><h1 id="important-update-for-older-liquidmix-instructions">Important Update for Older LiquidMix Instructions</h1>Earlier LiquidMix documentation instructed users to checkout the compatibility revision:<code>98403d3634a9a3bf929451e0d1a362345e59d982</code>and then run:<code>install_Anima38BV2EmbeddedLoader.py</code>That installation procedure is now obsolete.The current Semantic Connector v2 implementation requires files that were introduced after that older revision, including <code>semantic_connector_v2.py</code>.Therefore, do not checkout the old <code>98403d...</code> revision for the current workflow.Instead, install or update to the current version of:<code>GumGum10/comfyui-anima-3-8B</code>Using the current repository is recommended rather than pinning the installation to the old LiquidMix compatibility commit.<hr /><h1 id="current-installation-procedure">Current Installation Procedure</h1><h2 id="new-installation">New installation</h2><pre><code>cd ComfyUI/custom_nodes
git clone https://github.com/GumGum10/comfyui-anima-3-8B.git
</code></pre>Then install the dependencies:<pre><code>python -m pip install -r ComfyUI/custom_nodes/comfyui-anima-3-8B/requirements.txt
</code></pre>For ComfyUI Windows Portable, use the bundled Python executable instead.Example:<pre><code>C:\ComfyUI\python_embeded\python.exe -m pip install -r C:\ComfyUI\ComfyUI\custom_nodes\comfyui-anima-3-8B\requirements.txt
</code></pre>Then fully restart ComfyUI.<h2 id="existing-installation">Existing installation</h2>If <code>comfyui-anima-3-8B</code> is already installed:<pre><code>cd ComfyUI/custom_nodes/comfyui-anima-3-8B
git pull
</code></pre>Then update its requirements and restart ComfyUI.There is no need to checkout revision <code>98403d...</code>, run <code>install_Anima38BV2EmbeddedLoader.py</code>, or manually patch the package.<hr /><h1 id="current-semantic-connector-v2-workflow">Current Semantic Connector v2 Workflow</h1>The current Anima 3.8B LiquidMix workflow uses both:<code>qwen_3_06b_base.safetensors</code>and:<code>qwen35_4b.safetensors</code>The model path is:<code>Anima3.8B_LiquidMix_v4.03D.safetensors</code>→ <code>Anima38BV2Loader</code>→ optional LoRA loader→ <code>KSampler</code>The conditioning path is:<code>Native Qwen 0.6B</code><ul><li></li></ul><code>Qwen3.5 4B</code>→ <code>Anima38BV2Prompt</code>→ <code>expanded</code>→ <code>KSampler</code>Qwen3.5 4B does not simply replace the native Qwen 0.6B encoder.Both encoders are used as part of the current Semantic Connector v2 conditioning path.

Files with SHA256: 43b0a2e70866375e3da61399146cf8e0a6a865faaf916b3095af46429aedad7f