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
19 shown of 30,460
[Pony XL] Change-A-Character: Jiangshi-ify Your Waifu!
[For Pony SDXL and relevant checkpoints made through it]
Ernie Image Turbo Mlx Q8
Int8 quantization (groupsize 64, attention and FFN Linear weights only, leaving the small projections and the VAE in bf16) of dgrauet/ernie-image-turbo-mlx, the MLX conversion of baidu/ERNIE-Image-Turbo.
Videoprism Public v1 Large
VideoPrism is a family of foundational video-encoder models from Google Research, designed to be a universal "prism" for understanding the diverse facets of video content. Built on a massive scale of 36 million...
Grok Oss Apollyon 24B Heretic GGUF
For a convenient overview and download list, visit our model page for this model.
Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-MTP-Q8_0.gguf
Orion Chatbot
Developed by: [More Information Needed] Funded by [optional]: [More Information Needed] Shared by [optional]: [More Information Needed] Model type: [More Information Needed] Language(s) (NLP): [More Information...
flux2_klein_9b_base_fp8_V3.safetensors
[krea2] semi-real & illustration lora(harustyle)
Similar to version 1.5V face
Yufine (Epic Seven)
Yufine from Epic Seven.
Whisper Base Genai
openai/whisper-base exported to ONNX Runtime GenAI format with separate encoder and decoder ONNX files plus external data files.
XL_neco-arc
kohakudelta使用 Kohaku-XL Delta - rev1 |稳定扩散检查点 |奇维泰
krea2_raw_fp8_scaled.safetensors
Houki shinonono - (Infinite Stratos) - Commession - Anima Update
Houki shinonono - (Infinite Stratos) - Commession
Satsuki Kei Style for [illustrious][NoobAI]
如有要求,将予以删除 Will remove if requested
Flower LoRA Weights
LoRA fine-tuned weights for Stable Diffusion v1.5 trained on the Oxford-102 Flowers dataset.
Gemma 3 1b Kbd Q4km
A fine-tuned Gemma 3 1B (INT4) for context-aware text prediction on Android, quantized to GGUF Q4KM for on-device inference via llama.cpp.
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
Wesker Project 3.2 1B I1 GGUF
For a convenient overview and download list, visit our model page for this model.
