Am I the only one who gets terrible faces with the SD 2.1 base model?

ci_cd_crusader · 2026-08-14T09:56:37Z

I've been conducting a rigorous comparison of SD 1.5 and 2.1 base models for a synthetic image generation pipeline, and the results are concerning. Specifically, the facial outputs from the SD 2.1 base model (`stable-diffusion-2-1`) are consistently subpar—distorted features, asymmetrical eyes, and a general "uncanny valley" effect that 1.5 rarely produces at equivalent settings. My hypothesis is that this isn't just about the model checkpoint, but the interplay between model architecture, the negative prompt, and the specific VAE. In my controlled tests, I've used the following parameters as a baseline: ```yaml checkpoint: v2-1_768-ema-pruned.ckpt sampler: Euler a steps: 25 cfg scale: 7 size: 768x768 prompt: "portrait photo of a woman, detailed eyes, professional photography" negative prompt: "deformed, blurry, bad anatomy" ``` Even with these, the facial coherence is markedly worse. I've observed: * Pronounced "melting" or merging of facial structures (e.g., cheekbone into hair). * Inconsistent rendering of fine details like eyelashes or teeth. * A higher propensity for grotesque distortions compared to 1.5, which seems more robust. Has anyone else replicated this in their workflows? More importantly, has anyone found a reliable configuration pattern or necessary preprocessing step to mitigate this with the 2.1 base? I'm considering whether this is a known regression that necessitates always defaulting to a dedicated portrait fine-tune (like `Realistic_Vision`) when faces are a priority, which adds complexity to the pipeline. --crusader

Page 2 / 2 Prev

Stable Diffusion Reviews

Last Post by eval_rookie_42 2 months ago

16 Posts

15 Users

0 Reactions

32 Views

RSS

eval_rookie_42

(@eval_rookie_42)

Honorable Member

Joined: 6 months ago

Posts: 445

14/08/2026 9:57 pm

I just started testing these models and I'm seeing the same thing with faces. You mentioned the VAE being part of the problem. Is swapping to the 1.5 VAE something you can just do in any UI, or does it require a more technical setup? I'm worried about messing things up.

Also, does using a lower CFG, like someone else said, help enough to avoid that "melting" look, or is it just a band-aid?

ReplyQuote

Page 2 / 2 Prev