Instructions to use zlymon/my-flux-upscaler-endpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use zlymon/my-flux-upscaler-endpoint with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("zlymon/my-flux-upscaler-endpoint", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
| # 在项目根目录下 | |
| from handler import EndpointHandler | |
| from PIL import Image | |
| handler = EndpointHandler(path=".") | |
| # 示例:使用远程示例图 | |
| payload = {"control_image": "https://huggingface.co/jasperai/Flux.1-dev-Controlnet-Upscaler/resolve/main/examples/input.jpg"} | |
| res = handler(payload) | |
| print(res[0]["image_base64"][:100], "...") # 输出首 100 个字符,检查 Base64 格式 | |