Open darshats opened 3 months ago
For what I observed in past experiences, SDXL can work with many different resolutions, and its performance does vary from one resolution to another when working with IP-Adapter. You don't have to stick to (listed) supported resolutions.
This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.
Please note that issues that do not follow the contributing guidelines are likely to be ignored.
Describe the bug
I am running IP adapter for 768x1344 which is one of the sdxl listed resolutions. I find that the output quality is much less than say regular 768x768 generations. I've attached sample images and code below. In this experiment 1080x768 seemed to get best output, but its not one of the supported resolutions @asomo
Reproduction
import torch from diffusers import StableDiffusionXLPipeline, StableDiffusionXLImg2ImgPipeline, ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL, UniPCMultistepScheduler from diffusers.image_processor import IPAdapterMaskProcessor from transformers import CLIPVisionModelWithProjection from controlnet_aux import AnylineDetector import cv2 import numpy as np from PIL import Image, ImageOps from huggingface_hub import hf_hub_download
def create_controlnet_pipes(image_encoder=None)->StableDiffusionXLControlNetPipeline:
get controlnet
def canny(image): image = np.array(image) low_threshold = 100 high_threshold = 200 image = cv2.Canny(image, low_threshold, high_threshold) image = image[:, :, None] image = np.concatenate([image, image, image], axis=2) return Image.fromarray(image)
if name == 'main':
crop different values like 0,0,1080,768 or 0,0,1280,768
Logs
No response
System Info
v0.28.2 diffusers
Who can help?
No response