Text-to-Image
Diffusers
Safetensors
StableDiffusionXLPipeline
playground

How can I set parameters to generate multiple different images in the same prompt?

#13
by obtion - opened

How can I set parameters to generate multiple different images in the same prompt?

Thanks a lot

Something like this. The num_images_per_prompt variable is useful for this.

steps = 75
scale = 7
num_images_per_prompt = 3
seed = torch.randint(0, 1000000, (1,)).item()
generator = torch.Generator(device=device).manual_seed(seed)
output = pipe(prompt, negative_prompt=negative_prompt, width=1024, height=1280, num_inference_steps=steps,
guidance_scale=scale, num_images_per_prompt=num_images_per_prompt, generator=generator)

obtion changed discussion status to closed

Sign up or log in to comment