Update: Replaced v. 260 with v. 261. Fixed "cycling inputs" pairing which was not working properly. Added indicator of loaded (or not) model in LM Studio. SID (Semantic Image Disassembler) is a VLM-based tool for prompt extraction, semantic style transfer, and image re-composition (de-summarization). It works with LM Studio (via local API) using Qwen3-VL-8B-Instruct or any similar vision-capable VLM (tested with Qwen3-VL and Gemma 3).SID separates inputs into Content (structure, subject, composition) and Style (lighting, materials, visual physics) using a structured JSON analysis stage. Different modes operate on this analysis without re-interpreting the input.<h3 id="inputs">Inputs</h3>SID has two inputs: Style and Content. Both inputs support images and text.<ul><li>Multiple images are supported for batch processing.</li><li>Only one text file per input is supported (multiple TXT files are not supported).</li><li>Text files are treated like wildcards: 1 line / 1 paragraph = 1 prompt.</li><li>File type does not affect logic — only which input slot is populated.</li></ul><h3 id="modes">Modes</h3><ul><li>Only "Styles" input used:<ul><li>Style DNA Extraction – extracts reusable visual physics (lighting, materials, energy behavior).</li><li>Full Prompt Extraction – reconstructs a complete, generation-ready prompt describing how the image is rendered.</li></ul></li><li>Only "Content" input used:<ul><li>De-summarization – the input is treated as a TL;DR / summary of a full scene. SID reasons about missing structure, environment, materials, and context to deduce a detailed “full picture” description.</li></ul></li><li>Styles + Content, both inputs used:<ul><li>Semantic Style Transfer – preserves subject, pose, and composition from Content and renders it using only the visual physics of Style.</li></ul></li></ul><h3 id="smart-pairing">Smart pairing</h3>When multiple images are provided, SID automatically selects an appropriate pairing strategy:<ul><li>one content → multiple style variations</li><li>multiple contents → one unified style</li><li>one-to-one batch pairing</li></ul>SID shows intermediate stages during execution, automatically logs all results. SID can be useful for creating LoRA datasets, by extracting a consistent style from as little as one reference image and applying it across multiple contents.<h3 id="requirements">Requirements</h3><ul><li>Python</li><li>LM Studio <a target="_blank" rel="ugc" href="https://lmstudio.ai/">https://lmstudio.ai/</a></li><li>Gradio</li></ul><h3 id="how-to-run">How to run</h3><ol><li>Install LM Studio</li><li>Download (I recommend downloading model using LM Studio internal search) and load a vision-capable VLM (e.g. Qwen3-VL-8B-Instruct)</li><li>Start the LM Studio Local Server (In Developer tab, port 1234)</li><li>Launch SID</li></ol>

Files with SHA256: 199bcc15bc37302a10982dd315dd99d8e101c39e849294c97c1131a8fb211d35