Instructions to use Runware/pony-v7-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Runware/pony-v7-base with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Runware/pony-v7-base", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
ComfyUI PonyNoise Node
Download
Overview
ComfyUI uses CPU noise by default to ensure consistency across different platforms, while diffusers use GPU noise by default. However, GPU noise generation may vary between different GPU models, although it typically remains consistent across the latest NVIDIA cards.
This custom node provides the flexibility to switch between GPU and CPU noise generation modes, enabling you to match diffusers output on the same machine when needed.
Usage
To get started with the PonyNoise node, please refer to the noise selection workflow which demonstrates proper configuration and integration with your generation pipeline.
Installation
- Download the ComfyUI_PonyNoise.zip file
- Extract the contents to your ComfyUI custom nodes directory
- Restart ComfyUI
- Load the workflow
Acknowledgments
Special thanks to Silver for adapting the ComfyUI Noise nodes and helping with workflows.