sd_img2img: Generate images with img2img

In sd2R: Stable Diffusion Image Generation

Generate images with img2img

Description

Generate images with img2img

Usage

sd_img2img(
  ctx,
  prompt,
  init_image,
  negative_prompt = "",
  mask = NULL,
  width = NULL,
  height = NULL,
  sample_method = SAMPLE_METHOD$EULER,
  sample_steps = 20L,
  cfg_scale = 7,
  seed = 42L,
  batch_count = 1L,
  scheduler = SCHEDULER$DISCRETE,
  clip_skip = -1L,
  strength = 0.75,
  eta = 0,
  flow_shift = NULL,
  vae_mode = "auto",
  vae_auto_threshold = 1048576L,
  vae_tile_size = 64L,
  vae_tile_overlap = 0.25,
  vae_tile_rel_x = NULL,
  vae_tile_rel_y = NULL,
  vae_tiling = NULL,
  cache_mode = c("off", "easy", "ucache"),
  cache_config = NULL
)

Arguments

ctx	SD context created by sd_ctx
prompt	Text prompt describing desired image
init_image	Init image in sd_image format. Use sd_load_image to load from file.
negative_prompt	Negative prompt (default "")
mask	Optional inpainting mask. A PNG file path, a numeric matrix [H, W] (values in 0..1 or 0..255), or a 1-channel SD image list. White (255) = regenerate that region, black (0) = keep the original. Must match the init image dimensions. When NULL (default) the whole image is denoised (plain img2img).
width	Image width in pixels (default 512)
height	Image height in pixels (default 512)
sample_method	Sampling method (see SAMPLE_METHOD)
sample_steps	Number of sampling steps (default 20)
cfg_scale	Classifier-free guidance scale (default 7.0)
seed	Random seed (-1 for random)
batch_count	Number of images to generate (default 1)
scheduler	Scheduler type (see SCHEDULER)
clip_skip	Number of CLIP layers to skip (-1 = auto)
strength	Denoising strength (0.0 = no change, 1.0 = full denoise, default 0.75)
eta	Eta parameter for DDIM-like samplers
flow_shift	Flow shift for flow-matching models (Flux, SD3). NULL (default) lets the model pick an architecture-specific value; set a numeric value to override. Ignored by non-flow models.
vae_mode	VAE processing mode: "normal" (no tiling), "tiled" (always tile), or "auto" (VRAM-aware: queries free GPU memory via Vulkan and compares against estimated peak VAE usage; tiles only when VRAM is insufficient). Default "auto".
vae_auto_threshold	Pixel area fallback threshold for vae_mode = "auto" when VRAM query is unavailable (no Vulkan, CPU backend, etc.). Tiling activates when width * height exceeds this value. Default 1048576L (1024x1024 pixels).
vae_tile_size	Tile size in latent pixels for tiled VAE (default 64). Ignored when vae_tile_rel_x/vae_tile_rel_y are set.
vae_tile_overlap	Overlap ratio between tiles, 0.0-0.5 (default 0.25)
vae_tile_rel_x	Relative tile width as fraction of latent width (0-1) or number of tiles (>1). NULL = use vae_tile_size. Takes priority over vae_tile_size.
vae_tile_rel_y	Relative tile height as fraction of latent height (0-1) or number of tiles (>1). NULL = use vae_tile_size. Takes priority over vae_tile_size.
vae_tiling	Deprecated. Use vae_mode instead. If TRUE, equivalent to vae_mode = "tiled".
cache_mode	Step caching mode: "off" (default), "easy" (EasyCache — skips redundant denoising steps), or "ucache" (UCache). Can speed up sampling 20-40% with minor quality impact.
cache_config	Optional fine-tuned cache config from sd_cache_params. Overrides cache_mode when provided.

Value

List of SD images

sd2R documentation built on June 19, 2026, 9:08 a.m.