Instructions to use ModelsLab/Pixelwave-Flux with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ModelsLab/Pixelwave-Flux with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ModelsLab/Pixelwave-Flux", torch_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
| license: mit | |
| base_model: | |
| - mikeyandfriends/PixelWave_FLUX.1-dev_03 | |
| library_name: diffusers | |
| ``` python | |
| pip install sentencepiece | |
| pip install tokenizer | |
| pip install accelerate | |
| pip install protobuf | |
| import torch | |
| from diffusers import FluxPipeline | |
| pipe = FluxPipeline.from_pretrained("ModelsLab/Pixelwave-Flux", torch_dtype=torch.bfloat16) | |
| pipe.to("cuda") | |
| prompt="close beutiful lady face" | |
| # Depending on the variant being used, the pipeline call will slightly vary. | |
| # Refer to the pipeline documentation for more details. | |
| image = pipe(prompt, num_inference_steps=15, guidance_scale=4.5).images[0] | |
| image.save("flux.png") | |
| ``` | |
|  |