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 27,741
This model was converted to GGUF format from lightonai/LightOnOCR-1B-1025 using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.
Reviews, Hearts, Likes etc. are very appreciated!
[If you cannot see the images, please try disabling the X/XXX filters in your display settings.]
another merger, last one for the batch
pipeline = DDPMPipeline.frompretrained('aesari/ddpm-celebahq-finetuned-butterflies-2epochs') image = pipeline().images[0] image
This model is a diffusion model for unconditional image generation of cute 🦋.
💜 Github | 🤗 Hugging Face | 📚 Cookbooks
This model is a diffusion model for unconditional image generation of cute 🦋.
Vision Encoder - DinoV2 + SigLIP @384px resolution. Why 2 vision encoders? Connector - MLP (Dino and SigLIP features are concatenated and then projected to Phi3 representation space) Language Model - Phi3 + LoRA...
Trigger words makes lora much stronger.
8.23更新:更新了文官的 下次想看什么针对性服装可以留言 对汉朝服装就行的针对性训练,旨在还原最接近汉朝传统服饰的基础上达到能和二次元画风相结合,多数素材取材于央视版的三国演义(不是新三国那个),所以还原最接近的也只是三国演义版的服装(免责声明,传统服饰考究党请自行回避)。 由于训练有部分真人素材的缘故,生成图片可能会出现真人情况,建议搭配画风使用 目前第一版只训练了武官的衣服:武弁大冠, 直ju(抱歉我实在打不出这个字:曹大佐音)袍,赤zhi, 冠上的鶡(he)毛用的hat feather控制(老三国的武官都有这个羽毛来着) 根据大家的反馈和反响可能会考虑做文官的那身黑色的,如果想要的话请在评论区留言~ 作者心路:前段时间去了趟山西旅游,地上古迹看山西真不是白说的,古人们的审美比现在的强的多得多,与其说现在的角色美术设计都是在用木头去雕刻复原一朵花,那古代的设计者和工匠们就是用一颗种子来种出一朵花。难以想象古代的工匠是以什么样的心态,什么样的心情下修建了那么多建筑和雕塑。我觉得追求潮流并不是唯一的美,千年前的古人的审美不一定比现在的我们低俗。 顺带说一句山西博物馆真的值得一去,我就是去看了才萌生的想做这个lora的想法的。不过这个lora也只是当作技术效果的探索,如果大家不是很喜欢这样的模型,我后续会做一些别的主题服装的增强效果,之前有人想看愚人众披风来着 模型反馈返图及约稿群:1072319527
