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 28,713
ECAPA-TDNN language identification model converted to MLX safetensors format for inference on Apple Silicon (Metal GPU).
Rae Taylor - I'm in Love with the Villainess / レイ=テイラー , Rei Teirā / 私の推しは悪役令嬢。 , Watashi no Oshi wa Akuyaku Reijō
We explore the Reward Backpropagation technique 1 2 to optimized the generated videos by Wan2.1-Fun for better alignment with human preferences. We provide the following pre-trained models (i.e. LoRAs) along with the...
A half test model attempting to generate Solar Flare from PvZ in her original design
Testing the new blue buzz Early Access.
Astine is one of my MXAI girls, sourced only from purely prompted images, no humans involved. Generated on 82 images created solely by prompts and bodysliders, 15 vectors, learning rate 0.004, 15 steps pr...
Juggernaut XL v5 by RunDiffusion
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
Works best at 0.75 weight.
Works best at 0.95 weight.
