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 28,584
6-bit MLX quantization of baidu/Unlimited-OCR -- a long-horizon document OCR / parsing model (DeepEncoder vision + DeepSeek-V2 MoE decoder) -- running natively on Apple Silicon via mlx-vlm.
Trained on some choice Niji v6 gens. My attempt at the semi-realistic style we all know and love, but for Z-image.
So I wanted to do something different and take all these different images I’ve collected in different trainings and create something. This became the Mix person series.
Works best at 0.75 weight.
> Model from the paper: An OpenMind for 3D medical vision self-supervised learning > Pre-training codebase used to create checkpoint: MIC-DKFZ/nnssl > Dataset: AnonRes/OpenMind > Downstream (segmentation)...
This model doesn't need a trigger word
This is a timm remapped, image encoder only variant of the original weights.
Character LoRA (v1) for the Anima model family — dual-purpose SFW + NSFW. Trained on 207 curated solo images with danbooru-tag captions (4 epochs, 1308 steps).
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.5617 Accuracy: 0.7838
