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
| # Dependency set validated end-to-end on 2026-09-16. Exact pins are | |
| # intentional: this is the environment known to run both published checkpoint | |
| # families, not a broader compatibility matrix. | |
| torch==2.4.0 | |
| torchvision==0.19.0 | |
| transformers==4.57.1 | |
| diffusers==0.36.0 | |
| accelerate==1.13.0 | |
| transformer-engine[pytorch]==1.11.0 | |
| safetensors==0.7.0 | |
| tokenizers==0.22.2 | |
| huggingface-hub==0.34.0 | |
| peft==0.17.0 | |
| numpy==1.23.1 | |
| Pillow==10.4.0 | |
| requests==2.32.3 | |
| tqdm==4.67.1 | |
| typing-extensions==4.15.0 | |
| # Optional FlashAttention 2 backend (validated: flash-attn==2.7.3). The CLI | |
| # default is eager attention; --attn-implementation flash_attention_2 needs | |
| # this package. | |
| # flash-attn==2.7.3 | |