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
19 shown of 28,919
4-bit quantized version of Qwen/Qwen3-ForcedAligner-0.6B for Apple Silicon inference via MLX.
Trained using a dataset built with my Dataset Builder. Obviously this character is belongs to Lucas Film and should not be used in a compromising way. It was more so a test to see how well krea 2 handles alien...
This model is a 13.74% smaller version of google/siglip2-giant-opt-patch16-384 optimized for Azerbaijani language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly...
Works best at 0.75 weight.
These weights are compressed-tensors (pack-quantized / int-quantized).
Please do not share it on other websites at will. I will upload it myself if possible.At least ask for my own opinion first.
Works best at 0.75 weight.
If you like what I do, you can support me on my Ko-Fi:
Works best at 0.75 weight.
This model is a diffusion model for unconditional image generation of cute 🦋.
