Resource directory
Search Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
19 shown of 29,800
another merger using i2i adetailer and reactor. used DENlauralit and DENalyxstarrMK2 for the look
Fine-tuned version of Qwen/Qwen2.5-VL-3B-Instruct for Optical Character Recognition (OCR) of Odia script using LoRA adapters.
another merger using a VAM model as a base.
Model creator: torchvision Original model: efficientnetb6
Base Model: Animagine XL V3.1
This model is a 13.74% smaller version of google/siglip2-giant-opt-patch16-384 optimized for Greek language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to the...
Quality-oriented MLX conversion of ibm-granite/granite-speech-4.1-2b for Apple Silicon. This is the autoregressive Granite Speech model, not the separate NAR variant.
Works best at 0.75 weight.