Sam Kumar
894706d782
LM Studio endpoint usage and remove base_url parameter from input definitions for consistency ♻️ (llm_studio_structured.py): refactor code to remove base_url parameter from describe_image and describe_video methods, relying on global LM Studio endpoint configuration ✨ (swiss-army-knife.js): add debug logging for model dropdown interactions to enhance traceability and debugging capabilities in the UI
1.7 KiB
1.7 KiB
Summary
Generates JSON-structured descriptions for a single image using LM Studio's schema-enforced responses. Default behavior targets photorealistic character analysis with the Visionary Image Architect system prompt that locks appearance, expression, pose, and clothing outputs for Wan 2.2 workflows.
Inputs
- LM Studio endpoint: configured globally in Swiss Army Knife settings (all nodes automatically consume it).
model_name: Any loaded LM Studio multimodal model (defaults toqwen3-vl-8b-thinking-mlx).image: IMAGE tensor to analyze.schema_preset: Choosesimple_descriptionorcharacter_analysis(default). Character mode uses the new architect prompt described above.system_prompt: Override instructions if you need a custom style.user_prompt: Free-form request text.temperature,top_p,max_tokens,verbose: Standard generation controls.
Outputs
json_output: The entire LM Studio response string.field_1…field_5: Individual schema fields mapped in order (appearance, expression, pose, clothing when usingcharacter_analysis).
Usage Tips
- Keep
schema_presetoncharacter_analysisto leverage the Visionary Image Architect default; switch tosimple_descriptionfor lightweight captions. - Use
verbose=Truewhile troubleshooting to inspect payloads and LM Studio errors in the console. - The system prompt enforces decisive wording—omit hedging phrases in your own overrides to maintain consistency.
- Downstream nodes can parse the JSON string or read the individual field outputs without extra string handling.