w-e-w
commented
1 year ago try something
go to settings > controlnet > enable Do not append detectmap to output
from my testing the info text is correctly saved to image files the only issue is just front webpage displaying the wrong info for the wrong imnage
since you have 4 commands you have 4 info text for 4 image and the web page doesn't know how to display the info correctly when you have 8 images returned due to controlnet
the info text is only updated when you click the first 4 images and not for the 4 after
the webpage assumes that the 2nd image should correspond to the 2nd infotext, but in fact the 2nd image is a part of the 1st image
BingcaiOfficial
Is there an existing issue for this?
What happened?
When I use "Script:prompts from file or textbox" And "ControlNet:batch,canny" to Generate Images,It always uses the first line of prompt text
Steps to reproduce the problem
1.Select Tag: Text to images 2.Use ControlNet v1.1.238, arg: Enable, Control Type: Canny, Batch then Input Directory(images) 3.Use Script,Prompt from file or textbox,List of prompt inputs: --prompt "anime minimalist, masterpiece, bestink splash,,(1boy, male focus, solo, tattoo, abs, facial hair, black hair, muscular, chain, pectorals, nipples, short hair, nude, muscular male, bara, goatee, chest tattoo :0.6)" --negative_prompt "(worst quality, low quality:1.4), (realistic, lip, nose, tooth, rouge, lipstick, eyeshadow:1.0), (abs, muscular, rib:1.0), bad_prompt_version2-neg, badhandv4, easyNegative"
--prompt "anime minimalist, masterpiece, bestink splash,,(multiple boys, male focus, shirt, facial hair, short hair, black hair, beard, yellow shirt, brown hair, jacket, 6+boys :0.6)" --negative_prompt "(worst quality, low quality:1.4), (realistic, lip, nose, tooth, rouge, lipstick, eyeshadow:1.0), (abs, muscular, rib:1.0), bad_prompt_version2-neg, badhandv4, easyNegative"
--prompt "anime minimalist, masterpiece, bestink splash,,(tattoo, male focus, muscular male, muscular, bara, facial hair, pectorals, multiple boys, abs, nipples, large pectorals, navel, arm tattoo, beard, short hair, black hair, chest tattoo, topless male, mature male, shoulder tattoo, looking at viewer, jacket, closed mouth :0.6)" --negative_prompt "(worst quality, low quality:1.4), (realistic, lip, nose, tooth, rouge, lipstick, eyeshadow:1.0), (abs, muscular, rib:1.0), bad_prompt_version2-neg, badhandv4, easyNegative"
--prompt "anime minimalist, masterpiece, bestink splash,,(no humans, scenery, sky, cloud, outdoors, day, blue sky, sunlight, fence, building, wall, plant, shadow :0.6)" --negative_prompt "(worst quality, low quality:1.4), (realistic, lip, nose, tooth, rouge, lipstick, eyeshadow:1.0), (abs, muscular, rib:1.0), bad_prompt_version2-neg, badhandv4, easyNegative"
4.Generate!
5.PNG info review:It always uses the first line of prompt text
ps. When I first used it, it was normal, but now it doesn't work anymore. After downloading it again, it works again, but the problem occurred again the second time I used it
What should have happened?
img1: uses the first line of prompt input text img2: uses the second line of prompt input text img3: uses the third line of prompt input text ...
Version or Commit where the problem happens
V1.5.1
What Python version are you running on ?
Python 3.10.x
What platforms do you use to access the UI ?
Windows
What device are you running WebUI on?
Nvidia GPUs (RTX 20 above)
Cross attention optimization
xformers
What browsers do you use to access the UI ?
No response
Command Line Arguments
List of extensions
No
Console logs
Additional information
No response