Is there a way to view the image along with the deleted post so I can identify what was actually deleted? It's hard to review and make a challenge if needed without the image to reference. I only post here, so there is no source to reference.

Relating to this, I did manage to figure out some of them thanks to an old window I was lucky enough to have open.

https://e6ai.net/posts/68263. The reason given was "Does not meet minimum quality standards (number of fingers)" however I can clearly count 4 fingers and a thumb on each hand. So this is certainly one I want to challenge.

https://e6ai.net/posts/68257. Does not meet minimum quality standards (hooves or paws?). You can see the individual toes. Yes the feet aren't in 4k. Also see https://www.science.org/content/article/how-many-toes-do-horses-have-new-study-suggests-radical-number-five. 5 toes and hoofs exist. And why can't I have a skunk taur with hardier feet? Look at hippogriffs. We're deep into fantasy anyways, and technically these are all hybrids of some form or fashion.

https://e6ai.net/posts/68256. Does not meet minimum quality standards (deformed hands). She has clawed hands. Not sure why this is called deformed???

https://e6ai.net/posts/68242. Does not meet minimum quality standards (different number of digits on each hand). I can confirm 5 fingers visible on her left hand, and 4 visible on the right. Seems like a pretty minor detail overall given the way this looks.

https://e6ai.net/posts/68228. Does not meet minimum quality standards (number of fingers). I can confirm she has 5 fingers, and the hands aren't in 4k and not super clear.

Also since when were standards laid in for the number of toes and fingers? That varies quite a bit depending on the species and hand/foot style. There are also variations even within a species.

I can understand the need for quality and content standards, but that's a tricky line. Art has a lot of history and lessons on that one. Just look at Picasso. I think some reasonable guidance can be laid out, but as it is its quite concerning. I haven't posted in awhile because of the changes I've seen lately, and decided to test the water out a bit. Not too happy to see my fears confirmed.

--- May or may not be worth adding. If I did this same thing 90% of FA, e621, and most furry art in general wouldn't be allowed to be posted because the tails are in the wrong place. I can very much understand the feeling that something isn't quite right, but that doesn't give me the right to judge everyone else's work because of it. That's why I want to post lots of pictures with the tail in the right place and how I like the hips and legs so that there is a small chance it will catch on and I'll start seeing it in more places. Years ago I started commissioning more cougars and other critters that I liked and wasn't seeing enough of. After awhile I started seeing more of them. I have seen a few artist change as well. So I'd like to think I had at least a little bit to do with that.

Hopefully the technology will catch up enough that even I can produced exactly what I envision in complete clarity. However as things are it's not there and I have to live within what it can produce. I don't have the time, inclination, or skill to go through the cleanup process that some folks do. I've really loved the explanations given on the forum by the way, and hope to see more. Looks like it's progressing, but not quite there yet. So a little understanding in the meantime and focus on the concepts being presented may be the best way forward. Otherwise it's all just very superficial.

crashbandit said:
Is there a way to view the image along with the deleted post so I can identify what was actually deleted? It's hard to review and make a challenge if needed without the image to reference. I only post here, so there is no source to reference.

Relating to this, I did manage to figure out some of them thanks to an old window I was lucky enough to have open.

https://e6ai.net/posts/68263. The reason given was "Does not meet minimum quality standards (number of fingers)" however I can clearly count 4 fingers and a thumb on each hand. So this is certainly one I want to challenge.

https://e6ai.net/posts/68257. Does not meet minimum quality standards (hooves or paws?). You can see the individual toes. Yes the feet aren't in 4k. Also see https://www.science.org/content/article/how-many-toes-do-horses-have-new-study-suggests-radical-number-five. 5 toes and hoofs exist. And why can't I have a skunk taur with hardier feet? Look at hippogriffs. We're deep into fantasy anyways, and technically these are all hybrids of some form or fashion.

https://e6ai.net/posts/68256. Does not meet minimum quality standards (deformed hands). She has clawed hands. Not sure why this is called deformed???

https://e6ai.net/posts/68242. Does not meet minimum quality standards (different number of digits on each hand). I can confirm 5 fingers visible on her left hand, and 4 visible on the right. Seems like a pretty minor detail overall given the way this looks.

https://e6ai.net/posts/68228. Does not meet minimum quality standards (number of fingers). I can confirm she has 5 fingers, and the hands aren't in 4k and not super clear.

Also since when were standards laid in for the number of toes and fingers? That varies quite a bit depending on the species and hand/foot style. There are also variations even within a species.

I can understand the need for quality and content standards, but that's a tricky line. Art has a lot of history and lessons on that one. Just look at Picasso. I think some reasonable guidance can be laid out, but as it is its quite concerning. I haven't posted in awhile because of the changes I've seen lately, and decided to test the water out a bit. Not too happy to see my fears confirmed.

--- May or may not be worth adding. If I did this same thing 90% of FA, e621, and most furry art in general wouldn't be allowed to be posted because the tails are in the wrong place. I can very much understand the feeling that something isn't quite right, but that doesn't give me the right to judge everyone else's work because of it. That's why I want to post lots of pictures with the tail in the right place and how I like the hips and legs so that there is a small chance it will catch on and I'll start seeing it in more places. Years ago I started commissioning more cougars and other critters that I liked and wasn't seeing enough of. After awhile I started seeing more of them. I have seen a few artist change as well. So I'd like to think I had at least a little bit to do with that.

Hopefully the technology will catch up enough that even I can produced exactly what I envision in complete clarity. However as things are it's not there and I have to live within what it can produce. I don't have the time, inclination, or skill to go through the cleanup process that some folks do. I've really loved the explanations given on the forum by the way, and hope to see more. Looks like it's progressing, but not quite there yet. So a little understanding in the meantime and focus on the concepts being presented may be the best way forward. Otherwise it's all just very superficial.

You are correct about the first post, it has been returned to the gallery.

If you don't have the time or inclination to even attempt cleaning up clearly visible errors then perhaps reconsider if that image is worth posting at all. E6ai is not intended to be an archive where you can store every raw gen created but a curated collection of images that meet a bar of quality that honestly only asks for bare minimum effort put in.

jelloponies said:
You are correct about the first post, it has been returned to the gallery.

If you don't have the time or inclination to even attempt cleaning up clearly visible errors then perhaps reconsider if that image is worth posting at all. E6ai is not intended to be an archive where you can store every raw gen created but a curated collection of images that meet a bar of quality that honestly only asks for bare minimum effort put in.

Thank you. I can agree with not storing every raw image, but how do you define bare minimum effort? I'm using novelai which lacks tools to do corrections, and doesn't have the features I'm seeing on the bleeding edge releases. I also haven't gotten to the point of a working setup on my desktop yet to try out some of the other models. So the "effort" I put in is generating probably 50-150 images with tweaking settings and keywords for each just to get 1 or 2 that can be considered for posting. I don't really want to think about how many hours I've got in this, but I can say I've got 10's of thousands of generations for a small number that are good enough to be posted. The candidates get reviewed for upload consideration. It drives me nuts sometimes in that many of them are really close, but just a small bit off. So I don't really feel like I'm putting in zero effort. I'm limited by the tools at hand, and outside of custom setups I don't really see any better options out there for what I'm looking to get out of it. As such I do feel like I'm meeting the intent of this the quality standards listed here: https://e6ai.net/wiki_pages/uploading_guidelines#quality

What tools and such are out there these days to do the corrections?

crashbandit said:
I'm limited by the tools at hand, and outside of custom setups I don't really see any better options out there for what I'm looking to get out of it. As such I do feel like I'm meeting the intent of this the quality standards listed here: https://e6ai.net/wiki_pages/uploading_guidelines#quality

some problems can be fixed with simple, non-AI photo editing like cropping out signatures, hands with bad fingers, paws with odd numbers of toes, etc. can sometimes use a vignette effect to do the same thing. it's not always a solution just because you still need a decent image with reasonable composition or the problem is in the middle of the image, but it is a solution at least some of the time.

blp said:
some problems can be fixed with simple, non-AI photo editing like cropping out signatures, hands with bad fingers, paws with odd numbers of toes, etc. can sometimes use a vignette effect to do the same thing. it's not always a solution just because you still need a decent image with reasonable composition or the problem is in the middle of the image, but it is a solution at least some of the time.

Okay. I haven't thought about going to basics that much. I've been focused on preserving the whole image, and using AI to perform the corrections or avoiding the error in the first place. I focus a lot on movement and the scene so keeping everything in is generally important to me. I probably need to rethink this.

My impression is the better quality generations we're seeing today are due to a modification/add-on that can tag specific portions of the image, and using a base such as a sketch. Not sure how true that really is. The really good stuff seems to be from custom models and algorithms, but I don't have a lot of insight into those.

I'm used to the idea of going in manually and redrawing or manipulating an area to fix issues, which is super time consuming and I'm not skilled at. How do people go in and quickly make changes to say a hand or the eyes? I've seen some folks turn things around in a couple of minutes, which very likely moves it beyond doing it manually.

Novelai seems to be a year or so behind from what I can tell. I like novelai as it seems to generate better overall anatomy and texture, but it really seems to not do eyes well. It also doesn't seem to handle fingers and toes too well. Still trying to get something working on the desktop so I can try out some of the other things that exists today to see how they really compare. A lot of what I'm seeing generated I'm guessing is trained on a narrower dataset, and it produces the same errors I see a lot of artists produce. In fact that's getting worse, probably because it's more prolific.

----------------

Also before the original question is lost. Is there a way to view the image along with the deleted post so I can identify what was actually deleted? This is something I really want to figure out.

crashbandit said:
Okay. I haven't thought about going to basics that much. I've been focused on preserving the whole image, and using AI to perform the corrections or avoiding the error in the first place. I focus a lot on movement and the scene so keeping everything in is generally important to me. I probably need to rethink this.

well, if you don't want to change the image and the image doesn't meet e6ai's standards then something's got to give and it's probably going to be you. don't think you have much option other than not uploading the images in that case (or i guess letting them get removed, but would be a jerk move to create extra work for the janitors by posting stuff that they likely have to reject).

My impression is the better quality generations we're seeing today are due to a modification/add-on that can tag specific portions of the image, and using a base such as a sketch. Not sure how true that really is. The really good stuff seems to be from custom models and algorithms, but I don't have a lot of insight into those.

i haven't heard anything like that or used that sort of thing personally. models in generally have evolved, so fairly recent model is naturally going to be better at stuff like not creating abominations/messing up anatomy than a model from a year ago.

I'm used to the idea of going in manually and redrawing or manipulating an area to fix issues, which is super time consuming and I'm not skilled at. How do people go in and quickly make changes to say a hand or the eyes? I've seen some folks turn things around in a couple of minutes, which very likely moves it beyond doing it manually.

they're almost certainly using inpainting - you can mask off a specific region like a hand or an eye and just regenerate that part without changing the rest of the images.

Novelai seems to be a year or so behind from what I can tell. I like novelai as it seems to generate better overall anatomy and texture, but it really seems to not do eyes well. It also doesn't seem to handle fingers and toes too well. Still trying to get something working on the desktop so I can try out some of the other things that exists today to see how they really compare. A lot of what I'm seeing generated I'm guessing is trained on a narrower dataset, and it produces the same errors I see a lot of artists produce. In fact that's getting worse, probably because it's more prolific.

the main thing for local generation is having a good enough GPU. also for stuff like inpainting you don't _necessarily_ have to use the same model as the original generation, just something close enough that the changes will blend in. so if you really like how novelai does the initial generations and you can't find something else that works for local generation you could still do your cleanup locally with different models potentially.

Also before the original question is lost. Is there a way to view the image along with the deleted post so I can identify what was actually deleted? This is something I really want to figure out.

not as far as i know, and i agree it's pretty annoying that you can't. you basically have to figure it out from the image tags. it is possible to search for the images that have been deleted directorname status:deleted and approval is super timely these days so you shouldn't need to remember image tags for more than a day or so. also there probably isn't anything stopping you from putting some kind of hint to yourself in the description that will help you identify images if they get deleted.

it would be better from a user perspective if the user could see the deleted image even if no one else could but something like that would require changes to the site code which is probably not very likely. there are also reasons why it doesn't work that way. extreme example: if someone uploaded something like child porn, we would not want to keep serving images of that from the site to them

crashbandit said:
Okay. I haven't thought about going to basics that much. I've been focused on preserving the whole image, and using AI to perform the corrections or avoiding the error in the first place. I focus a lot on movement and the scene so keeping everything in is generally important to me. I probably need to rethink this.

My impression is the better quality generations we're seeing today are due to a modification/add-on that can tag specific portions of the image, and using a base such as a sketch. Not sure how true that really is. The really good stuff seems to be from custom models and algorithms, but I don't have a lot of insight into those.

I'm used to the idea of going in manually and redrawing or manipulating an area to fix issues, which is super time consuming and I'm not skilled at. How do people go in and quickly make changes to say a hand or the eyes? I've seen some folks turn things around in a couple of minutes, which very likely moves it beyond doing it manually.

Novelai seems to be a year or so behind from what I can tell. I like novelai as it seems to generate better overall anatomy and texture, but it really seems to not do eyes well. It also doesn't seem to handle fingers and toes too well. Still trying to get something working on the desktop so I can try out some of the other things that exists today to see how they really compare. A lot of what I'm seeing generated I'm guessing is trained on a narrower dataset, and it produces the same errors I see a lot of artists produce. In fact that's getting worse, probably because it's more prolific.

----------------

Also before the original question is lost. Is there a way to view the image along with the deleted post so I can identify what was actually deleted? This is something I really want to figure out.

The clone tool is your friend. It's available in a lot of free photo editing software (krita for example) https://imgur.com/a/d06GfsF
If you learn how to use the clone tool you can fix pretty much anything.
The program I use is paint shop pro 2023 (which coincidentally is available for $1 for the next 16 days on humble bundle)

Also no, you can't view deleted images. That would defeat the purpose of them being deleted.

jelloponies said:
The clone tool is your friend. It's available in a lot of free photo editing software (krita for example) https://imgur.com/a/d06GfsF
If you learn how to use the clone tool you can fix pretty much anything.
The program I use is paint shop pro 2023 (which coincidentally is available for $1 for the next 16 days on humble bundle)

Also no, you can't view deleted images. That would defeat the purpose of them being deleted.

Interesting, that's not the tool I remember. Going to give paint shop pro a try. Thanks.

For the deleted images, I don't mean so that anyone can view them. Just the poster even if it's just a thumbnail. Something to give a clue about what it was is all that's needed.

blp said:
well, if you don't want to change the image and the image doesn't meet e6ai's standards then something's got to give and it's probably going to be you. don't think you have much option other than not uploading the images in that case (or i guess letting them get removed, but would be a jerk move to create extra work for the janitors by posting stuff that they likely have to reject).

i haven't heard anything like that or used that sort of thing personally. models in generally have evolved, so fairly recent model is naturally going to be better at stuff like not creating abominations/messing up anatomy than a model from a year ago.

they're almost certainly using inpainting - you can mask off a specific region like a hand or an eye and just regenerate that part without changing the rest of the images.

the main thing for local generation is having a good enough GPU. also for stuff like inpainting you don't _necessarily_ have to use the same model as the original generation, just something close enough that the changes will blend in. so if you really like how novelai does the initial generations and you can't find something else that works for local generation you could still do your cleanup locally with different models potentially.

not as far as i know, and i agree it's pretty annoying that you can't. you basically have to figure it out from the image tags. it is possible to search for the images that have been deleted directorname status:deleted and approval is super timely these days so you shouldn't need to remember image tags for more than a day or so. also there probably isn't anything stopping you from putting some kind of hint to yourself in the description that will help you identify images if they get deleted.

it would be better from a user perspective if the user could see the deleted image even if no one else could but something like that would require changes to the site code which is probably not very likely. there are also reasons why it doesn't work that way. extreme example: if someone uploaded something like child porn, we would not want to keep serving images of that from the site to them

That's an interesting thought and workflow. Going to have to research inpainting and the rest. Thanks! That might be a really good answer for me.

For deleting I can totally agree with that, though I would hope they do a real purge or quarantine and not just a soft delete which is the default action. I wouldn't think it would be difficult to have it show a thumbnail for soft deletes that only the poster can view. All the functionality is there, so it should just be a simple condition check if(viewer is poster & status is deleted) then display 250px image. They have to perform a check already to block the image from loading, so it should just be extending that a tad. In theory anyways.