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 26,739
In my journey to improve my character embedding skills, I sort of made Desiree. I cherrypicked the good results.
Curated Collection of Line Art : Every page from "Robot Heads" and "Future Cities" (published books I created as colouring-in books)
Use strength 0.7-1.0 , I think 0.9 is a good start; some details like the glove should be "baked" into the character. The ghost trap and proton pistol don't work well. I kept the "nurse" picture as an example of poor...
This TI is from the Waifu diffusion server: It is not my model, to see and support the original creator go to the server.
Sarah is not based on any real person, but is a great way to create consistent characters in SD. I hope you like her!
Krea 2 can generate PVC figures standalone, but this LoRA is a specialized texture enhancer designed to massively upgrade the material realism and premium plastic touch.
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...
Loving this model? Get the Pro version of my models here for exclusive perks and early access to unique resources.
Lion learns densly distributed weights as expected. But we do not consider the performance of the resulting module attractive, so we do not release it. Lion确实按照预期学习到了更稠密的权重,但我们不认为新的模组的性能更具有吸引力,因此我们没有发布该版本。
Trigger + Appearance: f4llingd3vil, extra arms, arthropod limbs, blood from eyes, nosebleed, blood from mouth, holding head, severed head, disembodied head, short hair, black hair, chef hat, closed eyes
This model is released under Fair-AI-Public-License-1.0-SD Plz check this website for more information: Freedom of Development ( freedevproject.org )
OK 这是我的第二个模型 线稿画风的lora(lycoris)推荐使用权重为1-0.7 提示词是unfinished 使用的时候可以通过( unfinished:1.3) 这种方式来控制线稿的强度 请注意质量词对画风造成的可能影响。使用 Animagine XL V3 作为底模
YamashitaMinatsu, 1girl, solo, blue hair, long hair, hairband, jewelry, green eyes, earrings, large breasts,
這是一個使用我的 Lomography New Petzval 85 Art Lens 與 Canon 40D, Canon 6D, Canon R6 所拍攝的相片來當作訓練集,所製作出來的特殊散景 LoHa。
Get early access to build and test build, be able to try all epochs and test them by yourself on Patreon or contact me for support on Discord
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.
I couldn't find a way to get a model to do this natively so I created some sample images using the Art of MTG embedding . It's a model that knows what a dryad is. I made a subject textual inversion which is now...
Trained on a dataset of high shutter speed captures of water in different lighting scenarios. Interesting to apply to anything. I would love to see what you create. Tip, use this embedding with the Depth Model in...
ControlNet++: All-in-one ControlNet for image generations and editing!
LOCON version of my Tsuruko Aoyama LORA. In my opinion the best girl in Love Hina followed by Mutsumi, Haruka and Kanako in that order.
