Generate an image with FLUX.1-schnell
Description
4-step distilled text-to-image generation (no classifier-free guidance): T5 + CLIP prompt encoding, flow-matching Euler denoising over the packed latent sequence, and 16-channel VAE decode. With phase offloading each component is the sole GPU tenant for its phase.
Usage
txt2img_flux(prompt, pipeline = NULL, width = 1024L, height = 1024L,
num_inference_steps = 4L, max_sequence_length = 256L, seed = NULL,
prompt_embeds = NULL, pooled_prompt_embeds = NULL,
save_file = TRUE, filename = NULL, verbose = TRUE, ...)
Arguments
prompt: Character. The prompt.pipeline: Aflux_pipelinefromflux_load_pipeline; NULL loads one (passing...through).num_inference_steps: Integer. Denoising steps (schnell: 4).max_sequence_length: Integer. T5 token length (schnell: 256).seed: Integer or NULL. Initial latents are drawn on the CPU, so a seed matches a Python diffusers run with a CPU generator.save_file: Logical. Write a PNG.filename: Output path (default derived from the prompt).verbose: Logical....: Passed toflux_load_pipelinewhenpipelineis NULL.width,height: Integers, divisible by 16.prompt_embeds,pooled_prompt_embeds: Optional precomputed text embeddings (skip the text encoders).
Value
Invisibly, list(image, metadata) where image is
an [H, W, 3] array in [0, 1].