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 30,159
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Works best at 0.75 weight.
RF-DETR Nano fine-tuned on WIDERFACE for single-class face detection. Exported to ONNX (opset 17, 384x384 input) so the same weights run in Python (via onnxruntime) and in the browser (via libreyolo-web).
This embedding was made specifically to create a consistent art style between all generated characters of my proof-of-concept dynamically AI generated visual novel game: Tensor Tales.
Dementor imitation (disguise) LoRA adapter — dataset writingprompts, seed 42.
A NonCausal Clarinet/Others separation model for the CAD2-Task2 baseline system.
pipeline = DDPMPipeline.frompretrained('chess-va/ddpm-celebahq-finetuned-butterflies-2epochs') image = pipeline().images[0] image
→ Get it now for much cheaper prices, skip the wait:
Support my work by subscribing to patreon!
This model is a 14.75% smaller version of google/siglip2-giant-opt-patch16-384 optimized for Korean language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to the...
Akium Prisma is an Anima checkpoint built around vivid colors, bold lighting, and a clean stylized look. It's tuned for expressive anime illustration and handles a good range of moods — from soft emotional shots to heavy neon and cyberpunk scenes. Colors come out saturated and punchy without getting messy, and it keeps solid linework even in busier images. Works great for portraits, character pieces, and atmospheric stuff. Recommended Settings Steps: 35 Sampler: Euler a, ER SDE, or Akium Scheduler: Beta
