Easy to use Lora Trainer(:3000) with ComfyUI(:8000) for testing and VsCode(:8888).<a target="_blank" rel="ugc" href="https://runpod.io/console/deploy?template=9j2tjwyxys&amp;ref=0eayrc3z">https://runpod.io/console/deploy?template=9j2tjwyxys&amp;ref=0eayrc3z</a> Has diffusion-pipe pre-installed on the containerFile Management UI needs some more work to streamline the process but can be run by going to<pre><code>
1. cd /workspace/file-manager
2. source /workspace/bcomfy/bin/activate
3. npm install
4. node app.js

visit the https://xxxxxxxxxxx-3000.proxy.runpod.net/</code></pre> Current functionalityCurrent functionality of file-manager<ol><li>Select a name from the Wan models on Hungging Face paste it to the file manager and it will download to the file (Needs better loading UI)</li><li>Uploads traning data = image and text files</li><li>Settings can modify the tomal files. Ensure whatever model you add is also added to the ckpt_path = 'Wan2.1-14b'</li><li>Manually run traning but hope to create a full ui that can do everything </li></ol>Use this method for now:Highly recommed to follow this Youtube tutorial on how to setup traning data. This template is fully setup with everything you need, so just skip to the traning part.<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/T_wmF98K-ew?si=vdLVNJelHhYZKMCr" start="0"></iframe></div><h2 id="file-manager-quick-start-guide-pq2szn55t">📁 File Manager - Quick Start Guide</h2><ol><li>Download Wan Models<ul><li>Select a model name from Hugging Face (e.g., <code>Wan-AI/Wan2.1-T2V-14B</code>)</li><li>Paste it into the file manager download field</li><li>Click download (Note: UI loading indicators will be improved in future updates)</li></ul></li><li>Upload Training Data<ul><li>Use the file manager to upload your training images and text files</li><li>Files will be automatically placed in the correct input directories</li></ul></li><li>Configure Settings<ul><li>Use the Settings tab to modify the TOML configuration files</li><li>Ensure your model path is correctly set in the configuration</li><li>Example: Verify <code>ckpt_path = '/workspace/diffusion-pipe/models/wan2.1-14b'</code> matches your model</li></ul></li><li>Start Training Manually<ul><li>Currently, training must be initiated via command line</li><li>Navigate to the correct directory and run the training command:</li></ul><pre><code>cd /workspace/diffusion-pipe
NCCL_P2P_DISABLE="1" NCCL_IB_DISABLE="1" deepspeed --num_gpus=1 train.py --deepspeed --config examples/wan_video.toml
</code></pre></li></ol>Future updates will include a complete UI for all training functions.

WAN 2.1 Lora Trainer - ComfyUI VSCode Full - T1.0

Creating a WebUI to handle Testing Data, Download Models and run traning (coming soon)

Files with SHA256: e2023f92d3cf0013055f27b28d3ce994bcfdac6c87d16e9e7f82a9f26819d66c