Download FLUX.1-schnell and build the quantized artifact
Description
Skips work already done: a valid quantized manifest short-circuits
the transformer download; cached files are not re-fetched. Needs
HF_TOKEN set for the gated repo (see the error message it
raises without one). The bf16 transformer source (~24 GB in the
HuggingFace cache) may be deleted after quantization.
Usage
download_flux1(quantize = TRUE, precision = c("nf4", "fp8"), output_dir = NULL,
text_encoders = TRUE, verbose = TRUE)
Arguments
quantize: Logical. Build the quantized artifact after downloading.precision: “nf4” (~7 GB, GPU-resident on 16 GB cards) or “fp8” (~12 GB, CPU-resident, streamed; near-bf16 quality).output_dir: Directory for the quantized artifact.text_encoders: Logical. Also fetch the CLIP + T5 text encoders, tokenizer, VAE, and scheduler config (~10 GB).verbose: Logical.
Value
Invisibly, a list with transformer_dir,
artifact_dir, and support (named file paths).