Disty0/sd3_randn_aura_vae · not working. image results is worse random noise with rainbow color

Jul 2

!pip install -q git+https://github.com/Disty0/diffusers.git@sd3_rms_norm_and_attentionless_vae

import torch
from diffusers import StableDiffusion3Pipeline
from diffusers.models import AutoencoderKL

pipe = StableDiffusion3Pipeline.from_pretrained("Disty0/sd3_randn_aura_vae", torch_dtype=torch.float16,
text_encoder_3=None,tokenizer_3=None)
pipe = pipe.to("cuda")

image = pipe(
"A cat holding a sign that says hello world",
negative_prompt="",
num_inference_steps=28,
guidance_scale=7.0,generator=torch.manual_seed(0)
).images[0]
image

Disty0

Owner Jul 2

randn in the name means random. This models is only for training purposes. Don't use it if you don't know what you are doing.

Disty0 changed discussion status to closed Jul 2

Disty0 changed discussion status to open Jul 2

Disty0 changed discussion status to closed Jul 30