 slahiri
|
f9bbb1e081
|
docs: add comprehensive VLM captioning documentation
- models.md: Supported models by tier (Quick/Standard/Detailed/Extreme)
- captioning.md: Complete VLM guide including:
- Captioning approaches (Booru tags, e621, natural language, hybrid)
- Model-specific recommendations for SD1.5/SDXL/Flux/Z-Image
- Detailed model specs for 14+ captioning models
- Vision model landscape (DINOv2, InternVL, SigLIP, etc.)
- Workflow patterns and ComfyUI nodes reference
Generated with Claude Code
|
2025-12-20 15:53:56 +05:30 |
|