Hugging Face's logo

LMucko
/
GBSAR-SMALL

Unconditional Image Generation
Diffusers
Safetensors
DDPMPipeline
Model card Files Community

Trained for 50 and 500 inference steps. Everything else is default as seen in diffusers/examples/train_unconditional.py

model = UNet2DModel(
    sample_size=256,
    in_channels=1,
    out_channels=1,
    layers_per_block=2,
    block_out_channels=(64, 64, 128, 128, 256, 256, 512, 512),
    down_block_types=(
        "DownBlock2D",
        "DownBlock2D",
        "DownBlock2D",
        "DownBlock2D",
        "DownBlock2D",
        "DownBlock2D",
        "AttnDownBlock2D",
        "DownBlock2D"
    ),
    up_block_types=(
        "UpBlock2D",
        "AttnUpBlock2D",
        "UpBlock2D",
        "UpBlock2D",
        "UpBlock2D",
        "UpBlock2D",
        "UpBlock2D",
        "UpBlock2D"
    ),
)
Downloads last month
30
Inference Providers NEW
Unconditional Image Generation
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The HF Inference API does not support unconditional-image-generation models for diffusers library.