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 29,551
基于ANIMA base训练,训练分辨率1024p
For a convenient overview and download list, visit our model page for this model.
Support my work by subscribing to patreon!
For a convenient overview and download list, visit our model page for this model.
G4-Moonlight-Dusk-26B-A4B was created through a merge combining Gemma-4-26B-A4B-Animus-V14.1-FFT , G4-MeroMero-26B-A4B , Esmeralda-Gemma4-26B-A4B , and Pantheon-Reasoning-26B-A4B-1.1 , using a custom method.
Support my work by subscribing to patreon!
Steps: 10, Sampler: DPM++ 2S a Karras, CFG scale: 7, Seed: 2316919499, Size: 512x640, Denoising strength: 0.5, Clip skip: 2, Hires upscale: 2, Hires steps: 10, Hires upscaler: R-ESRGAN 4x+
This repository contains the configurations and weights for the UNIVERSE++ and UNIVERSE models implemented in open-universe.
Works best at 0.75 weight.
Trained entirely on screencaps Works with other lora
专供flurry rock使用,详细见 InfiniteMoon/004rock at main ( huggingface.co )
This model was trained by wyz using universalsev1 recipe in espnet. More information can be found at
This DoRA was trained to improve dark image generation in vpred models.
