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 26,900
Cozy lora style for Krea 2
This model was trained to detect sea urchins using the YOLO11 architecture. Trained on open datasets to identify and locate urchins in various underwater conditions. Model Architecture: YOLO11x Task: Object Detection...
This model is built on the ResNet-18 CNN architecture and trained to distinguish film photographs from digital ones by analyzing differences in texture, color rendition, and overall visual characteristics. It...
Hey ! :) LoRA #3 is here.
This model is a fine-tuned version of minhvn1433/wav2vec2-base-vi-vlsp2020 on the MINHVN1433/VIMDNORTHPHOWHISPER - NA dataset. It achieves the following results on the evaluation set: Loss: 0.4188 Wer: 0.1419 Cer: 0.0869
Base model: LTXV 2.3 Trained words:
Works best at 0.75 weight.
trigger word for clow card: card \(medium\),clow card
A research release from Tushe — The Foundry
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.
Base model: LTXV 2.3 Trained words: furrytransformation1
A SigLIP 2 ViT (image encoder only) for timm. Equivalent to image tower from
