Number that guides the creation of your image. Same seed with the same prompt, parameters (sampling steps, cfg scale etc.) and the same model will produce the exact same image each time.
Default = -1 All images generated will get its own seed, making it different from the last image If want to make similar to last image click recycle button on side to get old seed
Master key to image, can recreate and adjust your image:
With seed can get almost exact same image
Here, I will be using the same prompt and seed for each generation, however I will be changing a small part of the overall prompt to show how the slight variation in prompts can change the overall image. The change in prompt will be highlighted in yellow.
Original
sitting,
long hair,
black hair,
short hair,
excited,
smirk,
crying with eyes open,
bikini,
Removed “scuba diver” prompt as it influences clothing bikini,
swimsuit,
crop top, cleavage,
indoors,
indoors, bedroom,
outdoors, city,
sunset,
masterpiece, best quality, 1girl, beautiful detailed eyes, perfect face, beautiful detailed face, looking at viewer, amazing sharp focus, ultra detailed, silver hair, large breasts, bodysuit, wetsuit, scuba diver, blue eyes, long hair, high ponytail, sleepy, sweat, breathing, soft skin, outdoors, poolside, afterglow
Negative prompt: (worst quality, low quality:1.4), (monochrome:1.3), (NSFW:1.4), 3d, text, frame, jpeg artifacts, grids, watermark, logo, username, text, flowers, particles, (missing fingers:1.3), bad hands,
Steps: 20, Sampler: DDIM, CFG scale: 8, Seed: 3934657044, Size: 448x576, Model hash: 6806d4c0f8, Model: anything3pruned, Denoising strength: 0.7, Clip skip: 2, Hires upscale: 1.85, Hires steps: 20, Hires upscaler: Latent (nearest-exact)