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 29,294
《重返未来:1999》游戏画风,在快成丹的时候因为某些原因容器中断,导致没能训练完成,稍微有一点欠拟合,可提高权重使用。推荐权重1.0-1.2。
Ranma, anime screencap, 1990s (style), long hair, Red hair, ponytail, blue eyes, 1girl, solo,
Works best at 0.75 weight.
Works best at 0.75 weight.
Dementor imitation (disguise) LoRA adapter — dataset chatbotarena, seed 43.
Lora-scale: 0.7-0.9 Trigger Words : aria aquarius, long hair, purple hair, multicolored hair, black hair, purple eyes, streaked hair
Here we have the third sister, rather late but better than never. Oh My Goddess is a strange series, Belldandy is great but can be a bit boring, Older Skuld is the best of the 3 and Urd is really nice when she acts...
View the announcements on my profile for information regarding requests/commissions.
This model was trained using the Indonesian Plate Number from Multi Sources dataset.
Character LoRA (v1) for the Anima model family. Trained on 209 curated solo images with danbooru-tag captions (4 epochs, 1308 steps).
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.
This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.5217 Accuracy: 0.8412
Works best at 0.75 weight.
