Instructions to use kingjones777/Ming-Image-0.1-Design-ROCm-INT8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kingjones777/Ming-Image-0.1-Design-ROCm-INT8 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("kingjones777/Ming-Image-0.1-Design-ROCm-INT8", 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
File size: 865 Bytes
da1a4ff | 1 2 3 4 5 6 7 8 | Decompose this image into 5 layers with the following specifications: Number of layers: 5 Layer 1: A large solid crimson-red circle in the upper-left quadrant, with a subtly uneven printed-like texture and no outline. Layer 2: A tall solid dark-green rectangular panel centered in the canvas, evenly filled with faint mottling and no border or visible text. Layer 3: A broad solid royal-blue isosceles triangle on the right, its sharp apex near the upper-middle area and flat base aligned close to the large green panel's bottom edge. Layer 4: A small solid golden-yellow square in the lower-left quadrant, with soft uneven fill texture, squared edges, and no text. Layer 5: Pale cool-gray canvas background spanning the whole composition, with a continuous dark charcoal-gray horizontal baseline running along the bottom edge behind the floating geometric shapes. |