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 29,943
Prebuilt HNPU artifacts for nvidia/canary-1b-flash, a public automatic speech recognition model.
Selin is a lovely woman who doesn't exist
Model Type: Multilabel Image classification / feature backbone Model Stats: Params: 134.0M FLOPs / MACs: 132.2G / 66.0G Image size: train = 384 x 384, test = 384 x 384 Dataset:...
These are the NeuCodec decoder weights, extracted to safetensors for use with a pure-Rust CPU decoder (ndarray + rustfft) — no native ONNX runtime, no PyTorch at inference.
This is an SDXL locon, which is only used for the original series of checkpoint to improve the quality of anime painting.
Originally posted to HuggingFace by sd-concepts-library Mildemelwe style on Stable Diffusion This is the concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the Stable...
This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.3212 Accuracy: 0.9102
LibreYOLO9T classification model trained on imagenette (10-class ImageNet subset).
another VAM creation.
fp16 Core ML (mlprogram) export of the v3e2ernnt variant of ai-sage/GigaAM-v3 - a 240M-parameter Conformer transducer for Russian speech recognition that emits punctuated, capitalized, normalized text end-to-end....
This model will help you improve faces in your SDXL image generations.
This model is a fine-tuned version of facebook/mask2former-swin-large-ade-semantic on the AllanK24/apple-dms-materials dataset. It achieves the following results on the evaluation set: Mean Iou: 0.4468 Mean Accuracy:...
Quantized version of vikhyatk/moondream2 for efficient browser deployment with Transformers.js.
