Instructions to use tugrulv89/image21-evaluation-cache with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use tugrulv89/image21-evaluation-cache with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("tugrulv89/image21-evaluation-cache", 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
Download handler/qwen21/Dockerfile from tugrulv89/image21-evaluation-cache: direct link, hf CLI and curl.
- Browser
- Download file 556 Bytes
-
https://huggingface.co/tugrulv89/image21-evaluation-cache/resolve/main/handler/qwen21/Dockerfile
- Command line
-
hf download hf://tugrulv89/image21-evaluation-cache/handler/qwen21/Dockerfile
-
curl -L -o Dockerfile https://huggingface.co/tugrulv89/image21-evaluation-cache/resolve/main/handler/qwen21/Dockerfile
556 Bytes
| FROM runpod/pytorch:2.4.0-py3.11-cuda12.4.1-devel-ubuntu22.04 | |
| WORKDIR /app | |
| RUN pip install --no-cache-dir --index-url https://download.pytorch.org/whl/cu128 torch==2.7.1 torchvision==0.22.1 \ | |
| && pip uninstall -y torchaudio | |
| COPY qwen21/requirements.txt . | |
| RUN pip install --no-cache-dir --ignore-installed cryptography \ | |
| && pip install --no-cache-dir -r requirements.txt | |
| ENV HF_HUB_CACHE=/runpod-volume/huggingface-cache/hub HF_HUB_OFFLINE=1 TRANSFORMERS_OFFLINE=1 HF_HUB_DISABLE_PROGRESS_BARS=1 | |
| COPY qwen21/handler.py . | |
| CMD ["python", "-u", "handler.py"] | |