Jump to content
You must now use your email address to sign in [click for more info] ×

AI picture generators urgently required


Recommended Posts

I totally agree with you, drstreit. This new AI-word to text and video technology is HUGE! HUGE!!!

There hasn't been anything in the creative industry since... the first computer.

Its a global 'pandemic' of creativity and is infinitely more exciting than anything I've ever seen. The buzz online is... electric.

Are people blind to it? To the possibilities? Don't fear it - embrace it. Its not going to destroy your jobs. It's going to make them more exciting, more creative again after years of the one true (but boring) image on brochures, books, leaflets and flyers, Internet banners, information memorandum covers from the investment banks (in which I worked for 20 years) to sell a product or tell a story, now we can have rich, juicy, imaginative and dreamlike (or nightmarish) imagery again like we did before when a designer had to creatively composite imagery to sell a product. Now the creative teams can work in conjunction with AI text to word art generators like Stable Diffusion, Disco Diffusion, DALL-E 2, Midjourney, Stability AI/Stable Diffusion, Craiyon,
Openart.ai etc.

Its so exciting! I'm excited... by the prospects, by the creativity it will bring to the industry, to book cover, video games, the film industry.

Surely, this is only the beginning!

If you can't see how this new technology will benefit you then... Wake up! Open your eyes to it. See how vast and how exciting this new AI-word to text and video technology will be for you as designers, as newcomers to the industry. There is going to be a flood of jobs for creative minds who embrace it NOW while it is fresh. While it is young. Young designers, it is another tool in your toolbox, another colour in your palette and aided with Affinity Photo and Designer and this new AI generated text to image technology you will be there amid the new 60s explosion of colourful art and design.

All I can say is... Wow! To witness and be a part of the union of Affinity Photo and AI generated imagery generators like Stable Diffusion or Midjourney...

Bravo! You're so right, drstreit. You can see the future while ohers can't. 'To sleep, perchance to dream'...

Look at all those sad Victorians who feared the motor car and the railway....

I posted this on the Affinity forum a few days ago:

 

Link to comment
Share on other sites

3 hours ago, DelN said:

All I can say is... Wow! To witness and be a part of the union of Affinity Photo and AI generated imagery generators like Stable Diffusion or Midjourney...

Why does there need to be a union? Just use the two. 

Mac Pro (Late 2013) Mac OS 12.7.4 
Affinity Designer 2.4.0 | Affinity Photo 2.4.0 | Affinity Publisher 2.4.0 | Beta versions as they appear.

I have never mastered color management, period, so I cannot help with that.

Link to comment
Share on other sites

14 minutes ago, Old Bruce said:

Why does there need to be a union? Just use the two. 

Because these things are only weeks old and are only starting to develop. New features will be outdrawing existing pictures while copying style and extending content, adding content aware parts into images etc. 

A very close workflow will define how efficient that is: With your argument, every use of filters would be useless, as you can always use a standalone software. But we use  integrated filters as that workflow is more effective.

Back to the topic opening: Serif does not have to do anything, beside giving us an SDK. Not doing it will hurt the tool suite the long run.

Nobody forces anybody to embrace or not AI in imaging - I just brought my daughter to her horse riding lesson, so enough people still seem to preferring horses to cars… 

Link to comment
Share on other sites

 So far  I used  a few AI  tools :

Simplygon    - nope, it's  still easier to do lods manually.   Simplygon, while now a part of Unreal,   still couldn't work efficiently  or does it for a few  typical subjects only.

AI selection in Photoshop  - nope , works ok only for kittens  and faces, nothing I ever needed.  Couldn't recognize a thing beyond those few subjects .   Other  AI tools in Photoshop is totally useless for me .

Ai keywording services for DAM soft.   -  do a huge mess of keywords . Same issue with recognizing subject as with AI selection in Photoshop.  Works fine for people  faces and that's all. To bad I never needed that.

I have been subscribed to what now Unity art engine  for a year.  

Probably the best AI tool for CG and textures  for the moment  .    Hardly used it at all during the year   because other then  for a few  very specific tasks it was pretty inconvenient.       Slow , not good enough preview, always doing anything but what  you actually wanted.    Lacking any perception how  repetitive the final material is looking.      I preferred to just use patch tool in Photoshop  instead of all that cool AI  material regeneration.

As much as I hate Substance Designer  it still miles ahead and much more useful  without any AI  even considering its pixel processor  and Fx nodes are surely  codded by mad scientists.

AI material  from photo generator  in Adobe Sampler.   Well , for high quality materials  not a chance.  Works fine only on very limited subjects and  the soft is inconvenient as hell either.

Videogames  materials  have lots of limitation you have to constantly  find workarounds for.  Not a chance AI could do it for you so far.   

AI unwrap   in Substance painter, Never worked right. Works like a rookie  doing its first UV unwrap in Blender . Totally useless.

 

In a word after all that fuss   I am so disappointed with AI .  My impression it's good only for deep fakes and that's all.

 

 

 

 

Link to comment
Share on other sites

1 hour ago, kirk23 said:

... always doing anything but what you actually wanted.

This.

Take a look at the "pigs in chiffon dresses at a party drinking champagne" pictures. Not one of them show pigs drinking. A complete fail as far as I am concerned. 

Mac Pro (Late 2013) Mac OS 12.7.4 
Affinity Designer 2.4.0 | Affinity Photo 2.4.0 | Affinity Publisher 2.4.0 | Beta versions as they appear.

I have never mastered color management, period, so I cannot help with that.

Link to comment
Share on other sites

Come on guys, you remind me of the stories of the first steam train passengers, who fainted from the neckbreaking speed of 20 km/h and were convinced that humanity would never strive to move that fast…

So the pigs dont drink? Just take them as PhotoShop 1.0, Microsoft Windows 3.1 or a Assembler Compiler against C#… These tools are incredible powerful today, weeks after their release. But they are already good enough to generate new images to again train them to get better, allowing Reinforcement Learning with billions of new connections per day.

And they show only percentages of what already exists, as the full models are not public, with especially Google not releasing because its „ too powerful“…

 

Link to comment
Share on other sites

A couple of facts remain. (1) The staff at Serif is limited, and they must set priorities as to what, if any, additional features need to be included; and (2) the lure of AI will entice a bunch of people, but many (perhaps the majority) will have no use for it. I would rather see Serif avoid wasting time on niche projects and spend more time on a more universally-needed project like creating an API for more advanced plug-in availability. If and when Serif opens up an API for others to create, for example, additional studio-like panels then someone will create an AI plug-in for Affinity Photo. Probably a whole bunch of someones.

Serif has already said that they are at work putting Javascript and an API into the Affinity suite, but that it will take time. "Be patient" was their advice, and I am sure they mean it. That having been said, though, opening up the application to outside coders will create a much more fertile environment for plug-ins and other add-ons. These may only satisfy a small number of users, but they might be considered deal-breakers for those users who feel they need them. The availability of AI artwork within Photo is, I believe, one such niche market.

Affinity Photo 2, Affinity Publisher 2, Affinity Designer 2 (latest retail versions) - desktop & iPad
Culling - FastRawViewer; Raw Developer - Capture One Pro; Asset Management - Photo Supreme
Mac Studio with M2 Max (2023}; 64 GB RAM; macOS 13 (Ventura); Mac Studio Display - iPad Air 4th Gen; iPadOS 17

Link to comment
Share on other sites

Hi,

Regarding the 'Pigs drinking champagne' images...

I put the images up because I thought they were fun. It only took a few seconds to type out the phrase I used and a few minutes to generate the images. If you are interested in this new (and exciting) technology, you have to spend time reading the instructions (and there’s a lot of it!) on how to use them, which prompts to use to generate better images on the various AI text to image generator websites like DALL-E 2, Midjourney, Stable Diffusion and Disco Diffusion (I didn't). I just wanted to bring it to Affinity's attention at this early stage in the technology development. 

You can put in phrases like 'in the style of [your favourite artist eg Gustav Klimt, Frank Frazetta, Leonardo da Vinci] and the image created will be in that artist's style. If you don't like what is produced, you can select one of the four output images and request other images based on it. Many of the images produced are exquisite, dark and nightmarish, others are fairy tale Disney quality, others (architectural) are - depending on the prompts you put in - modern and innovative. If really depends on what you want to achieve, which prompts you use and the time you are willing to spend experimenting...

There is currently a controversy that has erupted over the art prize awarded to the artist M Allen, who submitted an AI-generated piece of art at the Colorado State Fair - and won! And it really is quite beautiful...

This from aljazeera.com:

'Jason M Allen, 39, and his Theatre D’opera Spatial image beat more than a dozen other entries in the “digital arts/digitally-manipulated photography” category at the Colorado State Fair.'

also

https://www.nytimes.com/2022/09/02/technology/ai-artificial-intelligence-artists.html

Midjourney AI art

https://www.google.com/search?q=pinterest+midjourney+ai+art&client=tablet-android-samsung-nf-rev1&prmd=insv&sxsrf=ALiCzsZQ4loGq-DB3WopdOhapWSkS1A5VA:1663701711483&source=lnms&tbm=isch&sa=X&ved=2ahUKEwjNrJnsi6T6AhUWiVwKHdmwAkkQ_AUoAXoECAIQAQ&biw=712&bih=1138&dpr=2.25

Stable Diffusion AI art

https://www.google.com/search?q=stable+diffusion+art&tbm=isch&ved=2ahUKEwjVgpCEjaT6AhUKRhoKHeR-CEYQ2-cCegQIABAC&oq=stable+diffusion+art&gs_lcp=ChJtb2JpbGUtZ3dzLXdpei1pbWcQAzIECAAQGDIECAAQGDIECAAQGDIECAAQGDIECAAQGDoECCMQJzoFCAAQogQ6BwgjELACECdQ4ghYugtgnRJoAHAAeACAAWSIAd8CkgEDMy4xmAEAoAEBwAEB&sclient=mobile-gws-wiz-img&ei=DhQqY9XDBYqMaeT9obAE&bih=1138&biw=712&client=tablet-android-samsung-nf-rev1&prmd=insv

Disco Diffusion AI art

https://www.google.com/search?q=pinterest+disco+diffusion+ai+art&tbm=isch&ved=2ahUKEwjRqt-cjKT6AhUQ5IUKHf83AgIQ2-cCegQIABAC&oq=pinterest+disco+diffusion+ai+art&gs_lcp=ChJtb2JpbGUtZ3dzLXdpei1pbWcQAzIFCAAQogQ6BAgjECc6BAghEApQqB5Y00Ng90ZoAHAAeACAAaABiAG4DJIBBDExLjWYAQCgAQHAAQE&sclient=mobile-gws-wiz-img&ei=NRMqY5G8EZDIlwT_74gQ&bih=1138&biw=712&client=tablet-android-samsung-nf-rev1&prmd=insv

DALL-E 2 AI art

https://www.google.com/search?q=pinterest+dalle+2+ai+art&tbm=isch&ved=2ahUKEwj8neqhjKT6AhVLwYUKHbMlAPkQ2-cCegQIABAC&oq=pinterest+dalle+2+ai+art&gs_lcp=ChJtb2JpbGUtZ3dzLXdpei1pbWcQAzIFCAAQogQyBQgAEKIEOgQIIxAnOgQIABAYUNAJWOgyYMw3aAFwAHgAgAFmiAGiCZIBBDEyLjKYAQCgAQHAAQE&sclient=mobile-gws-wiz-img&ei=PxMqY7yCOsuClwSzy4DIDw&bih=1138&biw=712&client=tablet-android-samsung-nf-rev1&prmd=insv

 

 

 

 

Link to comment
Share on other sites

I'm with you, drstreit. This is going to EXPLODE! It's so exciting...

I wish I was still working in a Design environment. Your designs are only as big as your imagination, but with a little help...

I've been writing my dreams down for many years. Dreams are an untapped resource for inspiration and creativity. I have used them in my writing, in my illustration work and in my designs. You truly have no idea what creative ideas you can have access to by not writing them down.

These AI text to image generator are like having access to someone else's dreams and nightmare, like having access to the Akashic Records. It's another tool, another colour in your palette, yes, but a great tool to experiment with now, while it's still in its infancy.

If you think this is big now, wait a few months...

 

Link to comment
Share on other sites

Great example here, DeIN!

I honestly struggle how anyone fails to see the upcoming impact: These models are only released some weeks ago, looking at the speed they evolve, we are seeing a freshly hatched 🐣 here that will turn into a man-eating ostrich within years…

Lucky the one to have tamed it then… And everybody: Give them a try, they are honestly just great fun to experiment around!

Link to comment
Share on other sites

On 9/20/2022 at 12:34 AM, smadell said:

 If and when Serif opens up an API for others to create, for example, additional studio-like panels then someone will create an AI plug-in for Affinity Photo. Probably a whole bunch of someones.

I agree, a full fledged API would snowball all kind of plugins, AI included.

Even Adobe cannot create all content by themselves, so the rely on the community. I teceived the same feedback from Serif as you mention: „Long term  idea to have a SDK, no roadmap yet“.

I struggle to understand how one can release ANY software product nowadays without automation API… Seems like shooting your own foot a bit…

Link to comment
Share on other sites

I adore Affinity. I think they are to be applauded to take on such a tyrannical 'wicked queen' as Adobe, who have over the years purchased many iconic and wonderful graphics software from other companies only to strategically 'discontinue' them later, retiring such excellent software as Macromedia Freehand, Fireworks and Flash among others (Microsoft did the same with Creature House Expression).

Adobe are mercenery in their attitude to their users. It's their strategy. We do not matter to them. Their desire to rule, to be the the 'all-powerful, the big 'I am' in the industry, is well known and well documented. And they are. That's why, when they made the avaricious and unscrupulous decision to put their software in 'the cloud' and forced - yes, forced - their users to RENT their software, we 'lesser mortals' were ignored. We were insignificant, we did not matter to the great Adobe. We were not wealthy. We could not afford to rent our software. Some of us were victims of the economic downturn, had lost our jobs, others were struggling young designers just out of design school (but not yet in employment), others were simply enthusiasts with an interest in design. Pah! I am Adobe! (pounds chest with fists) You do not matter to me!

The individuals and small companies who broke their backs trying to afford (and thereby support) the expensive Adobe software, Photoshop, Illustrator and InDesign for years were simply forgotten, kicked out into the street, left lying in the dust. 'You are poor, you have no money, therefore you have no worth; you don't interest me. I seek to court the big guys, the ones with money...'

But Affinity DO care about their users - rich or poor. That is why they keep the cost of their software Photo, Designer and Publisher at an affordable price. And their users are loyal and have a serf's hatred of tyranny. No empire lasts forever.  Even Rome fell. Adobe's ruthless strategy will be it's downfall.

So have faith. Affinity are clever, it's troops are loyal. They will see what the new AI-generated text to image software can do, will be watching it's rise with great interest, I imagine, investigating it's potential, quietly confident. We have brought it to their attention. Their finances are not limitless like the grasping, avaricious old queen, Adobe, who sits astride her throne like a whore on a war horse, snapping her gnarled fingers and screaming orders at her expendable minion. Her troops are not loyal. She rules by fear. She knows we are there, but she may not see us coming...

Affinity is Strength.

 

Link to comment
Share on other sites

On 9/21/2022 at 6:53 PM, DelN said:

'Stable Diffusion' AI tool now available in Blender.

Dream Textures...

 

I haven't tried this  but the video itself  don't give me any incentive to even bother  trying.    It perfectly illustrates my disappointment in AI tools for textures .   Totally useless . Even  so simple subject as brick texture is visually repeating like hell.  Bricks are deformed  etc.

And all this before the fact that color RGB textures  is a last thing  you care about when create  any material for  games or movies.   It's depth/height  texture that is a base to everything else.  A thing you derive color , normal, roughness and everything else . A core thing of any material.     And AI so far are pretty bad with  generating height .  Just try Adobe Sampler AI.  

I am really looking for  de-lighting AI  but so far haven't seen anything good.    Removing lighting and shadows   from photogrammetry source images  is what could be a perfect AI  purpose   but I have yet to see anything  useful.   Well, actually  not from source images , they would  instantly turn to be useless for photogrammetry after that  , rather from final texture.      Any modern albedo/color texture should be deprived of any  shadows  or shading information at all. It should look very flat and incontrast , just a hue variations and that's all.           And all AI  tools I have seen so far just  do ancient old hipass  on them , nothing good.

   Perhaps it's not even an  AI  issue,  rather people who code it.   I have to talk  with  graphics programmers a lot at my job and  usually it's like a talk in between  blind and deaf.    Programmers who spent their whole life codding  visual  stuff   often don't see an absolutely obvious things . That is always  make me kind of stuck since  I often  even can't find right words  to explain something because its so damn obvious and self revealing . 

Same reason probably why all the  non-AI  tools for creating CG content are  looking like been created by mad scientist . You spend your whole life trying  to figure out their crazy logic and deal with their  monstrosity .

I once heard a story that still amazes me.  An artist turned businessmen  in US invented  lead paint tubes in 19 century . A metal known since antiquity. Before artists used pig bladders to keep their paints from drying .  Doing small holes in such bladder evry next day.   And they did  it for DAMN five  if nor more centuries .         I very much hope  AI wouldn't take five centuries to be  useful :)

 

 

Link to comment
Share on other sites

7 hours ago, DelN said:

Affinity is Strength.

 

Great text - and I fully agree!

Hence this post actually - I would really hate to see Serif fall because an industry trend was slept through (not only talking about AI, SDKs in general are must-have nowadays to be successful).

Unfortunately, this seems to be the case now: Without plugin interface, we cannot be active as community - with one, the number of plugins and tools would explode.

Its not even on the roadmap, so I fear its at minimum a year ahead of us: I just hope that is not too late.

Link to comment
Share on other sites

It's not too late, drstreit. It's early days yet. I'm sure Serif are shrewd in their investments, they have to be (unlike Adobe). I imagine they have people watching these new technologies develope and evolve, and study them closely- especially the exciting new AI generated text to image software that has everyone so animated recently and stirred up such an enthusiastic furore online, on YouTube and other sites that if they see something developing that will work in conjunction with their products (which are great!), they will approach them and enter into discussion about a possible alliance.

I have faith in Serif. They must have so many challenging new additions to the updates for Affinity Photo, Designer and Publisher that they have their developers working on right now - and then this happens! Boom-bah! The biggest advancement in design, film, video and other media since the first computer...

Who could have seen THAT coming? 

You saw it, recognised its potential right away (as did I and many others), while some were more cautious, and others feared it would take their jobs. No, this is just another tool. If anything it will CREATE jobs. I imagine many thousands over the next few years. Every company will be discussing it in meetings, studying it closely to see how it can benefit them and their products. Advertising agencies are already testing it, the film industry too. Many of the great new innovative film directors like Ridley Scott, Tim Burton, George Lucas, Guillermo del Toro, Spike Lee, Steve McQueen, to name but a few will all be investing time and money in this new and exciting technology... I guarantee it...

Link to comment
Share on other sites

Hi kirk23,

I haven't used 3D software for a few tears. I tried Max in its early years, Cinema 4D for a few years but that was 5 years ago now, Bryce (but that was many. many years ago, and it was very amateurish (I couldn't afford the £2,000 for Max then). it was a very surreal interface and the results were not very good. I loved Vue and Plant Factory (for creating plants), but they were bought out by another company (who absolutely decimated the number of users they had by not updating the software, not giving information, just hiding away behind their website for a few years. When they did announce an update, it was to be on a RENT-only (they call it, 'subscription' like Adobe. But it means 'Rent'; if you stop paying your subscription - you-re out, mate!)

You certainly know your stuff!😊

I'd be interested to know what program you use to create your seamless textures (or do you find them or purchase them online?). Personally, I have always used Painter - from version 5.0, years ago - but Affinity Photo has the amazing Tile layers, which I find easy to use, also I use 'Affine' to create seamless textures and amend them, ie. painting out the join lines (vertical and horizontal). But I guess you have checked out these methods and know more about it than me, working in the gaming industry.

But I just thought I'd mention it.

The 'Dream Textures' plug-in for Krita and AI-text to image software in general is perhaps not the right tool to be creating the quality of seamless textures you require at the moment. The technology is still in its infancy. But it's coming along leaps and bounds and many people are working on the software in the background and they're getting funding from big companies who see the potential of this new and exciting technology.

I'd love to see some of your work. Send a link. I'm sure it would help and encourage other young Affinity Photo/Designer users who want to get into the industry.

And I agree with you entirely... coders - not all of 'em - create what THEY envision the end product to be (despite being given a detailed brief and having endless meetings), and the prototype they have spent many months developing is often far from user friendly and is often lacking in design and functionality. 'Ah well,' as my mum used to say, 'it's all for the sake'...

 

 

On 9/24/2022 at 5:58 AM, kirk23 said:

I haven't tried this  but the video itself  don't give me any incentive to even bother  trying.    It perfectly illustrates my disappointment in AI tools for textures .   Totally useless . Even  so simple subject as brick texture is visually repeating like hell.  Bricks are deformed  etc.

And all this before the fact that color RGB textures  is a last thing  you care about when create  any material for  games or movies.   It's depth/height  texture that is a base to everything else.  A thing you derive color , normal, roughness and everything else . A core thing of any material.     And AI so far are pretty bad with  generating height .  Just try Adobe Sampler AI.  

I am really looking for  de-lighting AI  but so far haven't seen anything good.    Removing lighting and shadows   from photogrammetry source images  is what could be a perfect AI  purpose   but I have yet to see anything  useful.   Well, actually  not from source images , they would  instantly turn to be useless for photogrammetry after that  , rather from final texture.      Any modern albedo/color texture should be deprived of any  shadows  or shading information at all. It should look very flat and incontrast , just a hue variations and that's all.           And all AI  tools I have seen so far just  do ancient old hipass  on them , nothing good.

   Perhaps it's not even an  AI  issue,  rather people who code it.   I have to talk  with  graphics programmers a lot at my job and  usually it's like a talk in between  blind and deaf.    Programmers who spent their whole life codding  visual  stuff   often don't see an absolutely obvious things . That is always  make me kind of stuck since  I often  even can't find right words  to explain something because its so damn obvious and self revealing . 

Same reason probably why all the  non-AI  tools for creating CG content are  looking like been created by mad scientist . You spend your whole life trying  to figure out their crazy logic and deal with their  monstrosity .

I once heard a story that still amazes me.  An artist turned businessmen  in US invented  lead paint tubes in 19 century . A metal known since antiquity. Before artists used pig bladders to keep their paints from drying .  Doing small holes in such bladder evry next day.   And they did  it for DAMN five  if nor more centuries .         I very much hope  AI wouldn't take five centuries to be  useful :)

 

 

 

Link to comment
Share on other sites

1 hour ago, Twolane said:

Here's a question for the AI afficionados: Whose images did you access and use? Did you use or access any of my images for your AI creation? If you did, did you get copyright permission?

Very much uncharted territory here: Would you sue an artist that looks at your pictures, gets a creative vision and goes home and starts painting? Can you really convince us, that you NEVER looked in your life on the work of others and somehow developed your unique style with that impressions as a basis?

And its also the other way around: AI generated picture also can have their IP protected - see here!

One big failure of any IP discussion is the acknowledgement that we all only develop EVERYTHING in our life while copying others behaviour, ideas, art, whatever.

That does not make it right to produce a 1:1 copy of anything - but it will grant you a new IP if the innovation/creativity barrier has been crossed: And that definitely is the case in AI generated images if you compare them to the training sets...

 

Link to comment
Share on other sites

There is a difference between getting inspiration from someone else's work, and just taking it and messing about with it!

Acer XC-895 : Core i5-10400 Hexa-core 2.90 GHz :  32GB RAM : Intel UHD Graphics 630 : Windows 10 Home
Affinity Publisher 2 : Affinity Photo 2 : Affinity Designer 2 : (latest release versions) on desktop and iPad

Link to comment
Share on other sites

On 9/25/2022 at 12:38 PM, Twolane said:

Here's a question for the AI afficionados: Whose images did you access and use? Did you use or access any of my images for your AI creation? If you did, did you get copyright permission?

Here the link to the training set of pictures currently used - you can check there if anything from your portfolio was used - and you can exclude it: https://laion-aesthetic.datasette.io/laion-aesthetic-6pls/images?_sort=rowid

 

Link to comment
Share on other sites

Hi @drstreit

Here's clip from the project page (https://waxy.org/2022/08/exploring-12-million-of-the-images-used-to-train-stable-diffusions-image-generator/) for that dataset:

image.png.5782d9857135a23461ef56b42b3db669.png

Also, I didn't see where you can go to have your images excluded do you have a link for that.

The copyright issue is discussed briefly on the comments on that page but there are no answers.

Link to comment
Share on other sites

On 9/25/2022 at 12:41 PM, DelN said:

Hi kirk23,

I haven't used 3D software for a few tears. I tried Max in its early years, Cinema 4D for a few years but that was 5 years ago now, Bryce (but that was many. many years ago, and it was very amateurish (I couldn't afford the £2,000 for Max then). it was a very surreal interface and the results were not very good. I loved Vue and Plant Factory (for creating plants), but they were bought out by another company (who absolutely decimated the number of users they had by not updating the software, not giving information, just hiding away behind their website for a few years. When they did announce an update, it was to be on a RENT-only (they call it, 'subscription' like Adobe. But it means 'Rent'; if you stop paying your subscription - you-re out, mate!)

You certainly know your stuff!😊

I'd be interested to know what program you use to create your seamless textures (or do you find them or purchase them online?). Personally, I have always used Painter - from version 5.0, years ago - but Affinity Photo has the amazing Tile layers, which I find easy to use, also I use 'Affine' to create seamless textures and amend them, ie. painting out the join lines (vertical and horizontal). But I guess you have checked out these methods and know more about it than me, working in the gaming industry.

But I just thought I'd mention it.

The 'Dream Textures' plug-in for Krita and AI-text to image software in general is perhaps not the right tool to be creating the quality of seamless textures you require at the moment. The technology is still in its infancy. But it's coming along leaps and bounds and many people are working on the software in the background and they're getting funding from big companies who see the potential of this new and exciting technology.

I'd love to see some of your work. Send a link. I'm sure it would help and encourage other young Affinity Photo/Designer users who want to get into the industry.

And I agree with you entirely... coders - not all of 'em - create what THEY envision the end product to be (despite being given a detailed brief and having endless meetings), and the prototype they have spent many months developing is often far from user friendly and is often lacking in design and functionality. 'Ah well,' as my mum used to say, 'it's all for the sake'...

 

 

 

To share any work I have to get my company permission first.  Don't  have  any portfolio  for 20 years already,  just no time to do something outside of the job .  But it's mostly scene environment  stuff anyway.  Nothing  spectacular.

As of seamless textures  I use Substance Designer  and  Painter  mostly.   They are industry standard now .     Since Photoshop released  pattern preview I  use it  to do    photogrammetry based textures   tilable sometimes,  thanks   to Photoshop  patch and content aware move  tools  +   record-able actions.    It is simpler and you have more control than with any of AI  tools I tried so far.      

Perhaps they are in its infancy state , yes   but I am waiting for 10 years already and  nothing  really helpful yet.   just toys.

  Affinity Tile layer is nice but kind of useless because of a number of Affinity limitations.    it's destructive  and you absolutely need   non-destructive tools to do  tilable textures now.  

 There is no convenient ones  unfortunately . Adobe Sampler  was a try to do one my guess but it's a pathetic fail imo.       

Also a half of my tilable textures is a bake from 3d software.   I use ClarisseFX  .   It has lots of easy  tools to scatter small things around and  nice baker .    Much quicker and better quality than  that non-stop pain in your ass  Substance Designer is .

 

 

Link to comment
Share on other sites

3 hours ago, Paul Mc said:

Hi @drstreit

Here's clip from the project page (https://waxy.org/2022/08/exploring-12-million-of-the-images-used-to-train-stable-diffusions-image-generator/) for that dataset:

Also, I didn't see where you can go to have your images excluded do you have a link for that.

The copyright issue is discussed briefly on the comments on that page but there are no answers.

Good reference! Yes, I also see the copyright problem being unsolved - and another huge challenge is also the fact that you can reverse engineer these models, to get back the training set data: Might not be too critical with art, but I work with health data and AI models...

Of course, I try to be the AI's advocate here in this post, so a bright side of these models: One can suffer the fact that these models do train on existing data - maybe even yours. Or you can make the power of the models your own asset: It needs surprisingly few pictures of a given style to train the mdoels to recreate that style.

That means you could easily extend the models with your own style (even locally, not making that public), and then utilize a model that mimics your own style for your work - adding unbelievable speed to your production pipeline...

Link to comment
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

Loading...
×
×
  • Create New...

Important Information

Terms of Use | Privacy Policy | Guidelines | We have placed cookies on your device to help make this website better. You can adjust your cookie settings, otherwise we'll assume you're okay to continue.