Stable Diffusion 3 requires users to accept the terms before downloading the checkpoint.

FLUX.1-dev also requires users to accept the terms before downloading the checkpoint.

Once you accept the terms, sign in with your Hugging Face hub READ token as below:

[!IMPORTANT] If using a fine-grained token, it is also necessary to edit permissions to allow Read access to contents of all public gated repos you can access

huggingface-cli login --token YOUR_HF_HUB_TOKEN

Step 1: Follow the installation steps from the previous section

Step 2: Verify you've accepted the StabilityAI license terms and have allowed gated access on your HuggingFace token

Step 3: Prepare the denoise model (MMDiT) Core ML model files (.mlpackage)

python -m python.src.diffusionkit.tests.torch2coreml.test_mmdit --sd3-ckpt-path stabilityai/stable-diffusion-3-medium --model-version 2b -o <output-mlpackages-directory> --latent-size {64, 128}

Step 4: Prepare the VAE Decoder Core ML model files (.mlpackage)

python -m python.src.diffusionkit.tests.torch2coreml.test_vae --sd3-ckpt-path stabilityai/stable-diffusion-3-medium -o <output-mlpackages-directory> --latent-size {64, 128}

Note:

• --sd3-ckpt-path can be a path any HuggingFace repo (e.g. stabilityai/stable-diffusion-3-medium) OR a path to a local sd3_medium.safetensors file

CLI

Most simple:

diffusionkit-cli --prompt "a photo of a cat" --output-path </path/to/output/image.png>

Some notable optional arguments for:

• Reproduciblity of results, use --seed
• image-to-image, use --image-path (path to input image) and --denoise (value between 0. and 1.)
• Enabling T5 encoder in SD3, use --t5 (FLUX must use T5 regardless of this argument)
• Different resolutions, use --height and --width
• Using a local checkpoint, use --local-ckpt </path/to/ckpt.safetensors> (e.g. ~/models/stable-diffusion-3-medium/sd3_medium.safetensors).

Please refer to the help menu for all available arguments: diffusionkit-cli -h.

Note: When using FLUX.1-dev, verify you've accepted the FLUX.1-dev licence and have allowed gated access on your HuggingFace token

Code

For Stable Diffusion 3:

from diffusionkit.mlx import DiffusionPipeline
pipeline = DiffusionPipeline(
  shift=3.0,
  use_t5=False,
  model_version="argmaxinc/mlx-stable-diffusion-3-medium",
  low_memory_mode=True,
  a16=True,
  w16=True,
)

For FLUX:

from diffusionkit.mlx import FluxPipeline
pipeline = FluxPipeline(
  shift=1.0,
  model_version="argmaxinc/mlx-FLUX.1-schnell", # model_version="argmaxinc/mlx-FLUX.1-dev" for FLUX.1-dev
  low_memory_mode=True,
  a16=True,
  w16=True,
)

Finally, to generate the image, use the generate_image() function:

HEIGHT = 512
WIDTH = 512
NUM_STEPS = 4  #  4 for FLUX.1-schnell, 50 for SD3 and FLUX.1-dev
CFG_WEIGHT = 0. # for FLUX.1-schnell, 5. for SD3

image, _ = pipeline.generate_image(
  "a photo of a cat",
  cfg_weight=CFG_WEIGHT,
  num_steps=NUM_STEPS,
  latent_size=(HEIGHT // 8, WIDTH // 8),
)

Some notable optional arguments:

• For image-to-image, use image_path (path to input image) and denoise (value between 0. and 1.) input variables.
• For seed, use seed input variable.
• For negative prompt, use negative_text input variable.

The generated image can be saved with:

image.save("path/to/save.png")

Core ML Swift

Apple Core ML Stable Diffusion is the initial Core ML backend for DiffusionKit. Stable Diffusion 3 support is upstreamed to that repository while we build the holistic Swift inference package.

MLX Swift

🚧