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 29,938
| Name | Onnx Runtime | PyTorch | | dbnetresnet18fpnc1200eicdar2015 | | | | dbnetresnet18fpnc1200etotaltext | | | | dbnetresnet50-dcnv2fpnc1200eicdar2015 | | | | dbnetresnet50-oclipfpnc1200eicdar2015 | | | |...
→ Get it now for much cheaper prices, skip the wait:
Developed by: ligaments-dev License: apache-2.0 Finetuned from model : unsloth/gemma-4-e4b-it-unsloth-bnb-4bit
timm PaliGemma2 (SigLIP image encoder only, with global avg pooling) weights from
This model is a diffusion model for unconditional image generation of cute 🦋.
> 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)...
> [!TIP] > KV-cache quantization without any fork (recommended, 2026): upstream > llama.cpp/Ollama now cover this natively — use -ctk q80 -ctv q80 > (half KV memory, negligible quality loss: perplexity +0.002–0.05)...
Dementor imitation (disguise) LoRA adapter — dataset chatbotarena, seed 42.
Works best at 0.75 weight.
This model is a fine-tuned version of Pengwin30/whisper-small-fine-tuned on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.0369 Wer: 1.3254
| Name | FLOPS | Params | Accuracy | AUC | Confusion | Labels | | caformers36v0 | 22.10G | 37.22M | 94.00% | 0.9913 | confusion | vision, imagery, halfbody, face | | mobilenetv3v0dist | 0.63G | 4.18M | 94.10% |...
another merger from my TI's
