Text-to-Image
Diffusers
English
StableDiffusionXLPipeline
stable-diffusion
stable-diffusion-xl
sdxl
hyper-sd
photorealistic
fast
low-step
juggernaut
rundiffusion
kandooai
Instructions to use RunDiffusion/Juggernaut-X-Hyper with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use RunDiffusion/Juggernaut-X-Hyper with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("RunDiffusion/Juggernaut-X-Hyper", 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
Parameters and what lora?
#1
by YaTharThShaRma999 - opened
what schedular and what parameters like guidance scale, negative prompt, and any others if needed should I use? Also, what lora did you merge into juggernaut? The 8 step or 4 step variant? I get somewhat blurry results?
@YaTharThShaRma999
DPM++ SDE (Karras is your choice)
5 to 6 Steps depending
1.5 to 2 CFG depending
The merge was actually a mix we found to work well with Juggernaut. Took a lot of testing to find our favorite.
It’s geared towards about 6 steps. This way we got more Juggernaut and less base SDXL