README
README
Text-only Documentation
Looking for the illustrated user documentation? https://github.com/ceveyne/draw-things-chat-docs
As it's questionable if simply plugging Draw Things into LM Studio might be of any benefit, enlightening your vision-capable Agent-Model with your generated images can sometimes be... surprising.
LM Studio Plugin: Draw Things supported by vision-capable Agents
For an overview of supported deployment scenarios (single machine, distributed, Linux server, runpod), see docs/DEPLOYMENT.md.
Do you already use models in the Draw Things app? Then you can start right away. draw-things-chat can use every model you use there. Without any configuration the models run with the "Recommended Settings" of Draw Things (plus tuned settings for some families). Name a model by family (krea_2), model name or file name; the tool lists what is installed. The presets below are only needed if you want different defaults, or a different model for a family. Very large output sizes use a second pass with SeedVR2 7B (any quantization), so install it in Draw Things if you want them.
text2image, image2image, edit, text2video and image2video modes by simply providing your favourite Draw-Things-settings for use with draw-things-chat:API Server: enable, ⚡️ gRPC Port: 7859, Transport Layer Security: enable, Response Compression: enable, Enable Model Browsing: enablevision-capability-primer:qwen/qwen3-vl-4b to your local computerqwen/qwen3.6-35b-a3b) to your server computerActivate the draw-things-chat plugin with the model-loader
Adjust the draw-things-chat plugin-settings to your local machine and network
vision-capability-primer:qwen/qwen3-vl-4b to your local computerqwen/qwen3.5-35b-a3b) to your server computerActivate the draw-things-chat plugin by choosing it from the model-loader
Adjust the draw-things-chat plugin-settings to your local machine and network: Disable the built-in tool 'generate_image()' to use any MCP-tool for image-generation that delivers base64 as tool-result.
text2image, image2image, edit, text2video and image2video modes by simply providing your favourite Draw-Things-settings for use with draw-things-chat:Draw-Things > Basic Settings > Load your preferences > Save as... text2image.auto, image2image.auto, edit.auto, ,
vision-capability-primer:qwen/qwen3-vl-4b to your local computerqwen/qwen3.5-35b-a3b) to your server computerActivate the draw-things-chat plugin with the model-loader
Adjust the draw-things-chat plugin-settings to your local machine and network
See the draw-things-index documentation for setup instructions.
See USER_GUIDE.md for in-depth documentation, use cases, technical requirements, known issues, and more.
See CHANGELOG.md for version history and release notes.
MIT
Text-only Documentation
Looking for the illustrated user documentation? https://github.com/ceveyne/draw-things-chat-docs
As it's questionable if simply plugging Draw Things into LM Studio might be of any benefit, enlightening your vision-capable Agent-Model with your generated images can sometimes be... surprising.
LM Studio Plugin: Draw Things supported by vision-capable Agents
For an overview of supported deployment scenarios (single machine, distributed, Linux server, runpod), see docs/DEPLOYMENT.md.
Do you already use models in the Draw Things app? Then you can start right away. draw-things-chat can use every model you use there. Without any configuration the models run with the "Recommended Settings" of Draw Things (plus tuned settings for some families). Name a model by family (krea_2), model name or file name; the tool lists what is installed. The presets below are only needed if you want different defaults, or a different model for a family. Very large output sizes use a second pass with SeedVR2 7B (any quantization), so install it in Draw Things if you want them.
text2image, image2image, edit, text2video and image2video modes by simply providing your favourite Draw-Things-settings for use with draw-things-chat:API Server: enable, ⚡️ gRPC Port: 7859, Transport Layer Security: enable, Response Compression: enable, Enable Model Browsing: enablevision-capability-primer:qwen/qwen3-vl-4b to your local computerqwen/qwen3.6-35b-a3b) to your server computerActivate the draw-things-chat plugin with the model-loader
Adjust the draw-things-chat plugin-settings to your local machine and network
vision-capability-primer:qwen/qwen3-vl-4b to your local computerqwen/qwen3.5-35b-a3b) to your server computerActivate the draw-things-chat plugin by choosing it from the model-loader
Adjust the draw-things-chat plugin-settings to your local machine and network: Disable the built-in tool 'generate_image()' to use any MCP-tool for image-generation that delivers base64 as tool-result.
text2image, image2image, edit, text2video and image2video modes by simply providing your favourite Draw-Things-settings for use with draw-things-chat:Draw-Things > Basic Settings > Load your preferences > Save as... text2image.auto, image2image.auto, edit.auto, ,
vision-capability-primer:qwen/qwen3-vl-4b to your local computerqwen/qwen3.5-35b-a3b) to your server computerActivate the draw-things-chat plugin with the model-loader
Adjust the draw-things-chat plugin-settings to your local machine and network
See the draw-things-index documentation for setup instructions.
See USER_GUIDE.md for in-depth documentation, use cases, technical requirements, known issues, and more.
See CHANGELOG.md for version history and release notes.
MIT
Draw-Things > Basic Settings > Load your preferences > Save as... text2image.auto, image2image.auto, edit.auto, text2video.auto, image2video.auto
<mode>.auto changes the settings of the default model of the mode, <mode>.<family> (e.g. text2image.krea_2) those of a model family including the model used, and <mode>.<your own name> is a preset you name freely. An image size saved in a text2image or text2video preset is used unless the agent asks for another one.
⚠️ Note: These settings are stored to <Your_configured_Model-Folder>/custom_configs.json. It might be a good idea to keep this file in sync with the one located inside your Default-Model-Folder (~/Library/Containers/com.liuliu.draw-things/Data/Documents/Models/custom_configs.json)
text2video.autoimage2video.auto⚠️ Note: These settings are stored to <Your_gRPC-configured_Model-Folder>/custom_configs.json. It might be a good idea to keep this file in sync with the one located inside your Default-Model-Folder (~/Library/Containers/com.liuliu.draw-things/Data/Documents/Models/custom_configs.json)
Draw-Things > Basic Settings > Load your preferences > Save as... text2image.auto, image2image.auto, edit.auto, text2video.auto, image2video.auto
<mode>.auto changes the settings of the default model of the mode, <mode>.<family> (e.g. text2image.krea_2) those of a model family including the model used, and <mode>.<your own name> is a preset you name freely. An image size saved in a text2image or text2video preset is used unless the agent asks for another one.
⚠️ Note: These settings are stored to <Your_configured_Model-Folder>/custom_configs.json. It might be a good idea to keep this file in sync with the one located inside your Default-Model-Folder (~/Library/Containers/com.liuliu.draw-things/Data/Documents/Models/custom_configs.json)
text2video.autoimage2video.auto⚠️ Note: These settings are stored to <Your_gRPC-configured_Model-Folder>/custom_configs.json. It might be a good idea to keep this file in sync with the one located inside your Default-Model-Folder (~/Library/Containers/com.liuliu.draw-things/Data/Documents/Models/custom_configs.json)