dream-dis-pix-xl

Dream Dis Pix XL

<Gallery />

(CivitAI)

Model description

<p><span>A (kinda failed) attempt to train an SDXL LoRA model upon on a mixed style dataset of images from </span><strong><span>Dream</span></strong><span>works, </span><strong><span>Dis</span></strong><span>ney and </span><strong><span>Pix</span></strong><span>ar. I have uploaded this</span><a rel="ugc" href="https://huggingface.co/datasets/Norod78/DreamDisPix-blip2-captions"><span> Blip2-Captioned Dataset to Huggingface</span></a><span>. </span><br /><br /><span>I usually prefer to train in LoRA ranks 4-16 because so far it always seemed to be enough and provided a reasonably small checkpoint but in this case, I only started getting results when I went for Rank-32, even tried 24 and it was not enough.</span><br /><br />M<span>y conclusion is that it should have probably been trained as several different lower ranked LoRAs each for the specific visual sub-style and it would have probably looked way better for each.</span></p>

Trigger words

You should use DreamDisPix style to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('Norod78/dream-dis-pix-xl', weight_name='SDXL-DreamDisPix-Lora-r32.safetensors')
image = pipeline('American gothic  DreamDisPix style  ').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers