Instructions to use prompthero/openjourney with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use prompthero/openjourney with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("prompthero/openjourney", 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
problem with highres .fix
I generate an image, and after executing highres .fix, it changes beyond recognition.
I use the openjourney-v2-unpruned model and webui from Automatic1111. with the key "--use-cpu all"
With other models, for example, 1-5-pruned, there is no such problem.
prompt: A (((cute little girl with loose hair))), against the ((background of a winter wood and Christmas tree)), full face, ((very high detailed face)), very high detailed ,sharp focus, elegant, render, octane, detailed, award winning photo, -ar 2:3, –beta, –upbeta, HD, cinematography, photorealistic, Ultra-Wide Angle, hyper-detailed, beautifully color-coded, insane details, intricate details, beautifully color graded, Natural Lighting, Incandescent, Optical Fiber, Moody Lighting, Cinematic Lighting, Studio Lighting, Soft Lighting, Ray Tracing Global Illumination, Scattering, Glowing, Shadows, Rough, Shimmering, Ray Tracing Reflections, Lumen Reflections, Screen Space Reflections, Diffraction Grading, Chromatic Aberration, GB Displacement, Scan Lines, Ray Tracing Ambient Occlusion, Shaders, Post Processing, Post-Production, Tone Mapping, hyper realistic, super detailed, 8k -q 2 -v 4
Negative prompt: hands
Steps: 50, Sampler: Euler a, CFG scale: 12, Seed: 1683359402, Size: 256x356, Model hash: b895edc4, Denoising strength: 0.7, First pass size: 0x0
before highres. fix
before face restoration