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 26,637
Negative embeddings for overall image quality and anatomy, should as well give you some more style consistency. These are some "fire-and-forget" negatives that don't really need much company and I don't really...
I'm hoping with this lora to achieve the feel of Anhes' bara art without sacrificing flexibility and ease of use. This version limits the dataset only his soft shaded bara art. So no Lush Puppies, digimon, etc. Lush...
Follow me to make sure you see new poses and Nobodys when I post them. Things move fast on this site, it's easy to miss.
This hypernetwork was trained on Anything-V3.0-pruned-fp32 [1a7df6b8] at a res of 512x768. The training dataset included primarily NSFW images and so the model leans heavily toward that type of content. All of the...
Here is another skin from the Le Sserafim x Overwatch collab ;D Hi-res fix and Adetailer or inpainting the face is heavily recommended. Weight: .8
Choi Rong (Sunbae) from Doki Doki Connection, a mature and curvy one of the three love interests of the MC. This turned out pretty good, considering the manhwa wasn't super detailed. It's also pretty flexible - I...
COBRA VICIOUS Cobra is not the typical mainstream girl, she grew up in an Igloo in the glaciers of Norway. She later became a famous V-Tube girl in Iceland where she dominated the scene with 9 subscribers, she is a...
Hypernetwork based on a selection of high quality images of Henri Rousseau's work. Rousseau was a French post-impressionist painter known for his vivid jungle scenes.
This is a Style which brings out a beautiful bridal aesthetic. Simply call Style-BridalSD2 in your prompt and your female characters will be ready for their wedding day!
Generated from fitness model images. if it creates green clothing just put color infront of your clothing prompt and/or add green negative prompts.
Join The Tinkerer on Whop. Membership gets you early releases, private tools and a bunch of extra stuff.
This embedding was very kindly created for me by nArno. Contains quality prompts for illustrious and some style prompts to nudge anime models closer to semi-realism. Generated with one of nArno's excellent AnBan...
NOTE: There are two versions of this character, an older (around 28-30 years old) and a younger (around 19-21). Switch versions via the buttons above the sample images.
Use at the beginning of the prompt when using more then one TI. Out of a batch of 8 a few will have the sides or one side of hair shaved. Depends on the strength of the other TI. I put a grid demo for an example of...
This embedding can be used to get improved results for female faces. The embedding causes stable diffusion to concentrate more on the face. Depending on the checkpoint, a weight between 0.5 and 3 is possible. Like...
This is my seventh publicly released Textual Inversion, called Style-Gravitymagic. This model was trained on a single image of a generated black hole using DreamArtist. This TI gives things a very vibrant colorful,...
So this one I wanted to make, but before I knew anything about lora training DeskGrenade agreed to make this one. He did a good job with it, and while I liked it, it had issues which I aimed to correct. The other...
Simple and effective embedding that makes images sharper and boosts contrast a bit. Works by specifically selecting "blur" concepts and pushing images away from them (if the embedding is put into negative, ofc)....
Introducing RFKTRplastic, This model has been trained specifically to enhance the plastic and 3D render-like qualities in your images, giving them a more modern and polished look.
