How to get intermeidate output images

John6666 · March 18, 2025, 6:02am

I think the same method can be used for the Diffusers pipeline.

Pipeline callbacks

Explanation of the 0.18215 factor in textual_inversion?

github.com/huggingface/diffusers

Explanation of the 0.18215 factor in textual_inversion?

opened 01:21AM - 09 Sep 22 UTC

closed 01:07PM - 09 Sep 22 UTC

garrett361

https://github.com/huggingface/diffusers/blob/b2b3b1a8ab83b020ecaf32f45de3ef2364…4331cf/examples/textual_inversion/textual_inversion.py#L501 Hi, just a small question about the quoted script above which is bothering me: where does this `0.18215` number come from? What computation is being done? Is it from some paper? I have seen the same factor elsewhere, too, without explanation. Any guidance would be very helpful, thanks!

Topic		Replies	Views
Got same resultant image while trying to re-use latents from a previous generation 🧨 Diffusers	1	272	May 22, 2023
GenAI Model/system every iteration visible Beginners	3	35	January 13, 2025
AutoencoderKL.scaling_factor and VaeImageProcessor 🧨 Diffusers	6	4215	August 29, 2023
Set latents in StableDiffusionInpaintPipeline to original image 🧨 Diffusers	1	623	May 17, 2024
Decoding latents to RGB without upscaling 🧨 Diffusers	12	11666	April 23, 2023

How to get intermeidate output images

Pipeline callbacks

Explanation of the 0.18215 factor in textual_inversion?

Related topics