Instructions to use openvivo/BluePixel-Turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use openvivo/BluePixel-Turbo 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("openvivo/BluePixel-Turbo", 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
comfy ui version when
please int8 convrot version or it will take another few months until we can test
We’re currently working on ComfyUI integration and quantized models. Both are coming soon!
We’re currently working on ComfyUI integration and quantized models. Both are coming soon!
can't wait to try it guys, i am rocking a vivo y21d phone in purple loving it and tried p-h3 image edit model it was underwhelming hopefully this vivo one surpasses it.
WAS Node Suite v3.10.0 provides native implementation ComfyUI support
https://huggingface.co/WAS/was-node-suite-weights/tree/main/models/bluepixel
Workflows:
Edit: https://github.com/WASasquatch/was-node-suite-comfyui/blob/main/docs/workflows/bluepixel-edit.json
Refine Edit Loop: https://github.com/WASasquatch/was-node-suite-comfyui/blob/main/docs/workflows/bluepixel-refine-loop.json
It's using custom nodes that are ComfyUI native, as WAS-NS isn't going to put in hard monkey patches on core. But it's still native implementation.
WAS-NS must be installed via Open Manger or directly via git clone https://github.com/WASasquatch/was-node-suite-comfyui (no deps to install by default so just clone and go).