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 27,238
This hypernetwork was trained on Anything-V3.0-pruned-fp32 [1a7df6b8] at a res of 512x768 and it's dataset included NSFW images. Additional checkpoints will be uploaded soon at various training steps. Edit: nvm...
Hi there! This is the Anima version. Don't expect too much from this model—I haven't been able to get the hang of training ANIMA LoRAs yet. I'm not sure if my dataset is the issue or if something in the training...
V67 Beautiful oriental painting 🎨🌸 – LoRA for Z-Image Turbo and Krea 2. Special Edition: Classical Chinese Beauty & Painterly Elegance
I feel that having just Kafka all alone is truly quite lonely,so I decide to invite all characters from Hongkai Star Raid to join.
Erin is an embedding trained entirely on AI prompted pictures (63 of them). She responds well to flowers, realistic and anime checkpoints and long walks on the beach. Trained on my usual 25 vectors with a learning...
SDXL LoRA/LyCORIS works best on the model that it was trained on. I will release multiple versions for a few popular models. Feel free to request for artist or model.
Latest page update: Updated recommended workflow again to a version 2, which is slightly even better.
Curated Collection of Neon Tokyopunk Artwork created under the pseudonym of Tomino sama by Freddy King, AKA Drift Johnson
This embedding was trained on 14 images taken from model cards from the original versions of other models of mine.
This is a Textual Inversion. Put the .pt file into your /embeddings folder inside the webui and use the triggerword. Might be overtrained. Kind of limited nsfw abilities. ̄\(ツ)/ ̄
If you find yourself struggling with the fine details of Hanfu prompt writing, you can completely skip describing the outfit and simply use the trigger word "neotangzhuang" instead.
I'd like to explain why I've stopped. Firstly, the expenses associated with renting Google Drive and server space were quite significant for me , plus I am grinding some game typical russian game with tech trees . I...
So I wanted to do something different and take all these different images I’ve collected in different trainings and create something. This became the Mix person series.
Originally posted to HuggingFace by sd-concepts-library Cute Game Style on Stable Diffusion This is the concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the Stable...
DoRA Weighting Note: SDXL Illustrious DoRA weighting begins at 0.0, with 0.05 - 0.4 as optimal range. Start at 0.0 and increasse by 0.01 to desired level.
Recommend Tags: twintails, double bun, hair ornament, vest, ribbon, bubble skirt, high-waist skirt, white gloves, thighhighs, choker, petticoat, high heels
LOCON version of my Lisa Pacifist LORA SD still seems to hate her hairstyle in this one but it is a lot more stable than the LORA version. I also got it a bit more stable rising the weight and adding hair bun,...
riamu yumemi, ahoge, blue hair, hair intakes, multicolored hair, (pink eyes:1.5), pink hair, short hair, two-tone hair,
Loving this model? Get the Pro version of my models here for exclusive perks and early access to unique resources.
My first textual inversion character. Sarah is not based on any real person, but is a great way to create consistent characters in SD. I hope you like her!
