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 27,077
Dual‐H3 Hierarchical‐Recombination Merge Dual‐H3 Hierarchical‐Recombination Merge is a merged checkpoint built with a custom hierarchical recombination technical pipeline based on two H3 base models. It adopts...
This TI is from the Waifu diffusion server: It is not my model, to see and support the original creator go to the server.
Some of my LoRA's stopped working on the latest Auto1111 version for some reason. Seems to be an issue with LoCon LoRA's. To fix it all you need to do is install this extension then you can use them as normal again!
My first try at making a textual inversion model and works most of the time. Trained as a subject and on mostly headshots and some full-body renders of Ahsoka Tano from Star Wars the Clone Wars.
Kṣitigarbha , a bodhisattva revered in East Asian Buddhism, is often depicted as a Buddhist monk. His name can be translated into various versions, such as "Earth Treasury," "Earth Store," "Earth Matrix," or "Earth...
提示词:Convert the image from anime style to a photorealistic scene with natural lighting, realistic skin textures, fabric detail, and soft ambient shadows, while maintaining the person’s exact facial expression, pose,...
In front of you are intrusive ads for prosthetics, micro armor, eye lenses, and shampoo. Savcorp will provide you with a dose of cyberpunk
Designed for ILXL 1.1, compatible with ILXL 2. and backports, but best on ILXL 1.1 and above. Anima ver is designed on Base 1.0 This is CUSTOMIZED ver.
4 vector TI embedding trained on 852 images (2280 augmented) of Akai Riot's work. Trained for 67,003 steps on animefull-latest.ckpt. Higher CFG tends to give stronger lines, also can adjust strength e.g....
This embedding was trained on 160 high quality close up photos of Preying Mantises in various poses.
Argenta (and I really have to stop naming aftwr hair colour) is trained on 100% AI generated images using ReActor to get the same face on all images.
Loving this model? Get the Pro version of my models here for exclusive perks and early access to unique resources.
The model data source is derived from Waifuc, a highly robust tool for crawling, filtering, and processing training sets. With the aid of the Waifuc tool and a single 5600g machine, it is possible to efficiently...
Lanolin Aries is a sheep girl with soft curls, oversized glasses, and the hesitant demeanor of someone who always seems halfway through working up the courage to say what she’s thinking. Like many sheep girls,...
This subject embedding is based on img2img generations I made based on Anime Expo's 2013 program guide:
The model data source is derived from Waifuc, a highly robust tool for crawling, filtering, and processing training sets. With the aid of the Waifuc tool and a single 5600g machine, it is possible to efficiently...
Originally posted to HuggingFace by sd-concepts-library sculptural style on Stable Diffusion This is the concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the Stable...
An 8 vector embedding trained on the style of a particular Japanese artist, trained on the NAI model.
My first attempt at an embedding. Trained on 30 images of the female uniforms from Star Trek Enterprise Mirror Universe Episodes. If anyone has any ideas to improve please let me know. Please leave an honest rating...
