I wanted to move a specific pipeline from Automatic1111 to a pure-code solution using hugging face diffusion pipeline. With the exact same parameter, the quality in the diffusers is worst. it uses instant id, realvisSDXLv40-lightning, guidance scale of 1, same prompt and negative prompt, seed, same …

Drastic outputs quality drops between Automatic1111 and Hugging face Diffusers

Swarzox July 3, 2024, 6:17pm 3

exact same issue with same model, did you find any workaround?

1 Like

Topic		Replies	Views
Notable differences between other implementations of stable diffusion, particularly in the img2img pipeline 🧨 Diffusers	10	4954	July 3, 2023
[Info Need]: Image2Image in Diffusers 🧨 Diffusers	2	463	May 16, 2023
How to reproduce results of huggingface api using diffuser 🤗Hub	0	200	December 27, 2023
How to increase quality of fine-tuned text-to-image LoRa? 🧨 Diffusers	0	1287	November 12, 2023
Only hosted models vs local models Beginners	1	127	February 9, 2025