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 26,621
the is a lora kairi from kingdom hearts 1 released in 2002, trained locally on a 5090/128gb ram build. trained at 5000 steps, 1024res, rank 32, automagic 3 and learning rate 0.0001. This lora was trained off of 37...
The model DOES NOT claim to be "well trained". The dataset was collected and tagged without proper attention to detail.
Works best at 0.75 weight.
I have a form for requests; check it out if you want to request a character.
Trained on both Disillusion and Disillusion ST screencaps
Support my work by subscribing to patreon!
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set: Loss: 2.6668 Accuracy: 0.0708
This model is a diffusion model for unconditional image generation of cute 🦋.
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.
use cfg: 1, steps 5-15, LCM sampling for fast generation
Originally posted to HuggingFace by sd-concepts-library princessknightart on Stable Diffusion This is the concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the Stable...
ltx-2-community-license
This model is a diffusion model for unconditional image generation of cute 🦋.
