| pipeline_tag: text-to-image | |
| library_name: diffusers | |
| tags: | |
| - modular-diffusers | |
| - diffusers | |
| - flux2 | |
| - text-to-image | |
| - modular-diffusers | |
| - diffusers | |
| - flux2 | |
| - text-to-image | |
| ## Setup | |
| Install the latest version of `diffusers` | |
| ```shell | |
| pip install git+https://github.com/huggingface/diffusers.git | |
| ``` | |
| Login to your Hugging Face account | |
| ```shell | |
| hf auth login | |
| ``` | |
| ## How to use | |
| The following code snippet demonstrates how to use the [Flux2](https://huggingface.co/black-forest-labs/FLUX.2-dev) modular pipeline with a remote text encoder and a 4bit quantized version of the DiT. It requires approximately 19GB of VRAM to generate an image. | |
| ```python | |
| import torch | |
| from diffusers.modular_pipelines.flux2 import ALL_BLOCKS | |
| from diffusers.modular_pipelines import SequentialPipelineBlocks | |
| blocks = SequentialPipelineBlocks.from_blocks_dict(ALL_BLOCKS['remote']) | |
| pipe = blocks.init_pipeline("diffusers/flux2-bnb-4bit-modular") | |
| pipe.load_components(torch_dtype=torch.bfloat16, device_map="cuda") | |
| prompt = "a photo of a cat" | |
| outputs = pipe(prompt=prompt, num_inference_steps=28, output="images") | |
| outputs[0].save("flux2-bnb-modular.png") | |
| ``` |