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 28,074
Loving this model? Get the Pro version of my models here for exclusive perks and early access to unique resources.
This is a DoRA , not your typically made LoRA . A1111 v1.9.0 and up is required to use this. Forge users must download two files, which can be found here . Go to stable-diffusion-webui\ldmpatched\modules and replace...
SDXL LoRA/LyCORIS works best on its original training model . You may need to reduce weight when using it with other models or additional LoRAs . LyCORIS Combination Recommendation: Try using four of my LyCORIS...
If you'd like to support me and do more: commissions open! If you're looking for a >>LoRA Making Tutorial
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.
This collection of embeddings is comparable to cinematic stills, film noir, photography, and hyperrealism in style selectors
Preview release focused on enhanced anime aesthetics, expressive full-body poses, natural anatomy, and dynamic body language. This version improves lighting, color harmony, refined linework, and cinematic...
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...
This model was trained off a few variations of Robert Motherwell's Elegy to the Spanish Republic Series. It can create variations of the Elegy to the Spanish Republic style in img2img. It mostly does a great job of...
Claire François - I'm in Love with the Villainess / クレア=フランソワ , Kurea Furansowa/ 私の推しは悪役令嬢。 , Watashi no Oshi wa Akuyaku Reijō
The lora evokes the feel of mid-century film stills, with cool twilight palettes and quiet, slightly uncanny American-night mood.
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...
ALOHA VICIOUS Jez is half Korean and half American and of course part of the gigantic Vicious family. They are nice people and gave birth to a lot of pretty daughters, the best about them is... they are entirely...
High frequency word: rindou mikoto:1.00,mole under mouth:0.94,thick eyebrows:0.89,oni:0.98,skin-covered horns:0.93
Trained based on kohaku-epsilon-rev2, setting the weight to 1 is fine. Used 1172 images generated by myself in NovelAI V3. The training parameters are as follows:
Weigths around 0.7-1 work well, but feel free experimenting with it. Most samples are created with my wildcards.
I just made a new Telegram Group and Discord group drop in for chats, questions, feedbacks or just to share your work. 欢迎加入 纸飞机 和 Discord 群组。
SDXL LoRA/LyCORIS works best on its original training model . You may need to reduce weight when using it with other models or additional LoRAs . LyCORIS Combination Recommendation: Try using four of my LyCORIS...
BEA VICIOUS BEA ia from the Austrian side of Vicious family (Austria = Mozart not Kangaroos) . They are nice people and gave birth to a lot of pretty daughters, the best about them is... they are entirely fictional....
This style model captures the dark, surreal essence of H.R. Giger and biopunk aesthetics. It perfectly fuses organic elements like bone structures, ribbed spinal columns, and glossy chitin shells with high-tech...
