Resource directory
Find what you need for your workflow.
Guides: techniques, setup, and troubleshootingSearch Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
All resources
20 shown of 38,689
Nico Robin (Post-TimeSkip) [One Piece] (Anima)
Join the Discord server too! You can request commissions and interact with the community members
XUPLX_UglyPeopleLoRA
XUPLX (UglyPeopleLoRA) is intended to break up the monotony of ZImage Turbo output by forcing interesting compositions, character designs, camera angles, action and other attributes into the output image by using...
[SDXL] Artist Style: Ohisashiburi
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...
Kawakami Rokkaku Style
If you like my content consider supporting me! 😊
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf
diffusion_pytorch_model.safetensors
Lagombi [1.5 & XL | Monster Hunter]
If you enjoy my content, consider supporting me on Ko-Fi ! ☕
Reno - Azur Lane - COMMISSION
reno, (purple eyes:1.1), short hair, white hair,
WAN-2.2-I2V-Double-Blowjob-HIGH-v1.safetensors
artist:murakami suigun
更新 一口气更新两个版本,一个是之前说的老画风,一个是新老画风在同一个lora里可以分开调用的多画风,老画风的启动词是@murakami suigun \(2000s\),而新版本是@murakami suigun。 另,我觉得双画风在一个Lora里会很炫酷,你们不觉得很炫酷吗。 以防你们不信以及不会翻到我证明一个丹两个画风,我把对比图放这 anima版本更新 其实anima会这个画师串,但是因为这个画师的画作时间跨度太长,所以取了比较新的时间的训练,这个Lora可以很好稳定在比较近期的风格,比画师串观感好的多,未来我会再炼一个怀旧画风的分支 V3更新 更好的还原度,更好的肢体,更好的兼容性,甚至更好的训练集 权重1.0 又新又好,啊不行我不能嘴角上翘。 V2更新 没什么好说的,全面的比1.0要好,建议直接换成V2.0。画风更像的同时还没有了以前老画风的污染情况,也不用将画师tag调成0.6-0.8了,并且兼容的模型我测下来更多了。 murakami suigun 的画师风格lora 权重建议0.6-0.8,注意,你的murakami suigun这个TAG也要0.6-0.8.原因是noob本身有这个画师TAG,但是学的不像又过拟合,这个lora主要解决tag不像的问题。 不使用启动词时是另一种风格
[+]Shimoe Koharu /下江小春/ 下江コハル | Blue Archive
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...
Riko Ichinose| Ran→Sem
一ノ瀬 莉子(いちのせ りこ)from Ran→Sem~白濁デルモ妻のミイラ捕り~
42ndAlignment Gpt Oss 20b Pref Sft LoRA v0.2
This is a LoRA adapter for unsloth/gpt-oss-20b-unsloth-bnb-4bit, trained as part of the 42ndAlignment project.
Llama 3.2 3B Instruct Grpo Ppl Adv Rollout 8 Resume Epoch10 20260429 004543 Step232
Giallostyle! Gritty 70's italian thriller
→ Get it now for much cheaper prices, skip the wait:
Irish style interior design
Irish style interior design draws on the country's rich history, natural beauty, and cultural traditions to create warm, inviting, and character-filled spaces. It's known for its blend of rustic charm and timeless...
Chinese Fondant Figure style-国风翻糖人偶风格
This is a fondant style model trained in the style of a master of fondant artistry from China. Unlike clay sculptures or plastic models, the unique pearlescent and reflective qualities of fondant figurines have been...
SEVEN V1 URDU
Bloom Fairy Transformations (Magic Winx To Dreamix) (Anime) | Winx Club
Works best at 0.95 weight.
