Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
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
20 shown of 26,846
New Update! I have re-tested this LoRA on-site and now, it works (with no action on my side). Welp, in any case, i have re-activated on-site usage :D
This is a Multimodal World Model architecture based on the Joint-Embedding Predictive Architecture (JEPA). It fuses the reasoning power of Qwen3-VL-4B-Thinking with the visual latent space of Stable Diffusion VAE.
Works best at 0.75 weight.
This model is a 14.75% smaller version of google/siglip2-giant-opt-patch16-384 optimized for German language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to the...
Works best at 0.75 weight.
Trigger + Additional Tag: cross-body stretch, stretching
The plan with this lora was simple: make an attractive character. The trick was to create a character that is undoubtedly pretty but not generic. I present to you the result of my rigorous slop-science experiments:...
Young Akagi : white shirt, collared shirt, short sleeves, white hair
Showcase prompts by who ordered the model.
This is an embedding of a woman that I've generated consistent faces of thru SD and decided to make into an embedding for easier access in the future. It uses a mere 5 tokens.
Works best at 0.75 weight.
Character LoRA (v1) for the Anima model family. Trained on 100 curated solo images with danbooru-tag captions (4 epochs, 1200 steps).
