Instructions to use RunDiffusion/Juggernaut-Z-Image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use RunDiffusion/Juggernaut-Z-Image 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-Z-Image", 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 Settings
- Draw Things
- DiffusionBee
Commit History
-
Move Diffusers format to repo root (fix #2: from_pretrained subfolder= does not work for whole pipelines)
Verified signaturesubfolder= on DiffusionPipeline.from_pretrained is for loading individual sub-component classes, not whole pipelines: it does not propagate to nested sub-model loading, so the previous diffusers/ subfolder layout broke from_pretrained for users (reported by @rpeinl in discussion #2). Moving model_index.json and the 5 component dirs (scheduler/, text_encoder/, tokenizer/, transformer/, vae/) to repo root, where DiffusionPipeline.from_pretrained will pick them up correctly. Repo continues to host the standalone .safetensors and .gguf variants at root; from_pretrained only downloads files declared in model_index.json.30ea709