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
19 shown of 26,690
Jubilee from Marvel Rivals. Trained on Illustrious-XL v0.1. Tested at 0.8-1.0 strength. Contains two outfits: Default , Midnight Mutant . Trigger Prompts
Base model: LTXV 2.3 Trained words:
In most image generation models, skin translucency is difficult to control precisely because there are few reliable tags that directly represent subsurface scattering.
This model is part of our ICASSP 2026 paper: Test-Time Adaptation Methods for Speech Emotion Recognition.
✨ Kayo Makabe from H ga Kirai na Iinchou ga Saimin Choukyou Sarete Mesu ni Sareru
ONNX export of patrickjohncyh/fashion-clip split into separate vision and text encoders. Hosted for use by @looped-app/garment-classifier as a third backbone option alongside the standard OpenAI CLIP variants from...
This model doesn't need a trigger word
tao71-license-111
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set: Loss: 0.0283 Accuracy: 0.993 Accuracy Ai: 0.9955 Accuracy Real:...
Another merger
This is a LoCon for generating a character in the Franky "Super" Pose of Cyborg Franky from One Piece. It provides more consistent results with less style bias than the standard lora versions as much as I can tell....
Shizune Tsurumi from Saijo no Osewa
Here's Priss The last of my Bubblegum crisis characters. As mentioned i n the LORA one this is trained on my dataset "A" which has some normalization but in exchanges eats most of the style.
GGUF / ggml conversion of oddadmix/lahgtna-chatterbox-v1 for use with CrispStrobe/CrispASR.
timm PaliGemma (SigLIP image encoder only, with global avg pooling) weights from
