stable diffusion is creating bad outputs.

3 years ago by heimchen to c/stable_diffusion

I just installed stable diffusion on my homelab and did not change anything, but the outputs are really bad, I tried following tutorials, but my version just outputs really weird stuff.

What am I doing wrong?

Lorez 3 points 3 years ago

The size (256x256) might be too small. Here's 512x512, and here's the same thing, but 256x256.

save

path: 0 264506, hotness: undefined, score: 3, children: 1

SweetAIBelle 2 points 3 years ago

I'd also suggest that using a different model (Deliberate 11, in this case), changing the prompt a bit, and using a negative embedding can help, even at 256x256.

an ai generated photograph of a woman with brown hair

Prompt: photograph of a woman with brown hair, portrait, masterpiece, trending on artstation
Negative prompt: easynegative
Steps: 20 | Sampler: Euler a | CFG scale: 7 | Seed: 2156939601 | Size: 256x256 | Model hash: 57d103206a | Model: deliberate_v11-pruned | VAE: vae-ft-mse-840000-ema-pruned | Clip skip: 1 | Version: 8749067 | Token merging ratio: 0.5 | Parser: Full parser

Used embeddings: easynegative [119b]

save

path: 0 264506 265247, hotness: undefined, score: 2, children: 0

Stampela 1 point 3 years ago

Too low resolution and not the best sampler are the main ones. Try again with those exact settings, same seed and same prompt BUT at 512x512 and you will get

save

path: 0 269952, hotness: undefined, score: 1, children: 2

heimchen 1 point 3 years ago

Changing resolution helped, do you have recommended Sampler.

save

path: 0 269952 277426, hotness: undefined, score: 1, children: 1

Fubarberry 1 point 3 years ago

DDIM is great for both fast results, and final results on non-realism images. You can set DDIM to 12 steps and get pretty solid results, which is great when you're wanting to quickly try prompt variations or search for really good seeds. I usually use 20 steps when getting a final image.

DPM++ is the best I've tried for realism results, but it's slower per step than DDIM and requires 35-40 steps to get good results imo.

save

path: 0 269952 277426 349180, hotness: undefined, score: 1, children: 0

josecastilloellion 1 point 3 years ago

I can't zoom in on your picture, but are you using any checkpoint models?

save

path: 0 305125, hotness: undefined, score: 1, children: 0

Also see

Other communities

Also see

Other communities