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 28,845
anima base v1.0无触发词(no tigger word)
A Taiwan-Mandarin reading variant of Luigi/matcha-zh-en-8k (itself an 8 kHz-distilled csukuangfj/matcha-icefall-zh-en). Only the lexicon differs — Taiwan reading choices replace the Mainland ones, so the model says...
推荐提示词:segment the character full body and turn it into a pixel-art-style chibi sprite, simple green background, chibi, A-pose, simple standing pose with hands down, facing right, big head with small body, simple...
Works best at 0.75 weight.
Arousal-valence dimensional emotion recognition from speech, built on ntu-spml/distilhubert.
View the announcements on my profile for information regarding requests/commissions.
My goal when training is good likeness with high flexibility for clothing. This model has proven more challenging than others, I may need to more carefully curate my dataset than I already have, but it works well enough.
