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 30,206
Reno from The Misfit of Demon King Academy
Works best at 0.75 weight.
A deliberately trivial MNIST convnet -- the champion selected by an Optuna search and registered in MLflow, exported here as TorchScript and served by revision from this repo.
This is a direct GGUF conversion of the LTXV-13B-0.9.8-dev variant from Lightricks/LTX-Video.
This model was created from the Mozilla.ai Blueprint: speech-to-text-finetune.
Drop-in replacement for the sherpa-onnx vits-melo-tts-zhen model directory, with the 44.1 kHz HiFi-GAN decoder replaced by a distilled 8 kHz Vocos-style vocoder (ConvNeXt @ 125 Hz + iSTFT head, 3.65 M params).
sugiura takako, short hair, brown hair, curly hair, hairclip, choppy bangs, brown eyes, purple-framed eyewear, under-rim eyewear, long sleeves, blue cardigan, hooded cardigan, white shirt, collared shirt, red...
Maintained by the xaitalk project as a fallback source so library users can always download Gemma 4 E2B even if the canonical Google repo becomes temporarily unavailable.
> [!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)...
Bortus was a Moclan Second Officer and Lieutenant Commander aboard the USS Orville.
restricted-research-evaluation
Base Model: Animagine XL V3.1
Support my work by subscribing to patreon!
