Author | Thread |
|
01/16/2025 11:29:07 AM · #1 |
This is a side challenge to showcase and experiment with AI generated images. It piggybacks on the regular challenge stream.
The rules of the game:
Pick a Challenge: Select any completed challenge as your reference.
Create with AI: Use any generative AI tool to produce an image for that challenge.
Upload Your Image: Share your creation with a fitting title.
Include Key Details: In the image comments, provide:
1. The reference challenge
2. The AI engine used
3. Your prompt (including any custom options and links to reference images if applicable)
Share Here: Post a thumbnail of your image in this thread, along with the challenge name and image title.
Important: Do not post images for ongoing challengesstick to completed ones!
|
|
|
01/16/2025 11:42:19 PM · #2 |
my conversation with ChatGPT
me: create an image of contre-jour vii
ChatGPT: Here is the image inspired by the concept of "contre-jour vii," showcasing a serene landscape with a backlit effect. Let me know if you'd like any adjustments!
me: i would like the sensation of ribbons radiating from the sun
ChatGPT: Here is the updated image with the sensation of ribbon-like beams radiating from the sun. Let me know if you'd like further refinements!
me: i would like something with a unique view on photography, something way more interesting than nick hinch
ChatGPT: To create something uniquely evocative in the realm of photography, we can explore concepts that challenge conventional perspectives. For example:
Fractured Reflections
An image captured through broken glass or fragmented mirrors, each shard reflecting a slightly different part of the same subject or scene. This creates a kaleidoscope of perspectives, challenging the viewer to piece together the narrative.
Invisible Subjects
A photograph where the primary subject is suggested through absencelike shadows, outlines, or the way light interacts with objects. This evokes a ghostly presence, making the viewer fill in the gaps.
Micro and Macro Juxtaposition
A seamless blend of macro photography (e.g., the intricate texture of a leaf or a droplet) with a distant landscape, creating a surreal sense of scale and connection.
Time Stitched Together
A long-exposure photograph that layers moments into a single frame, showing movement and stillness in harmony. For instance, a figure walking while trees sway, but their face remains sharp and focused.
Light and Shadow as Characters
A study where light and shadow themselves tell the story, becoming the primary "characters" in the frame, with the human or natural subject only implied.
Would you like me to generate a visual inspired by one of these ideas? Or do you have a different direction in mind?
me: please incorporate all these ideas into the image
ChatGPT: Here's the image inspired by the blend of unique photography concepts we discussed. It combines fractured reflections, invisible subjects, macro and macro juxtapositions, layered time, and the interplay of light and shadow. Let me know if there's anything else you'd like to explore! |
|
|
01/17/2025 10:02:25 AM · #3 |
Wow. What a useful post :-) Thanks! |
|
|
01/17/2025 10:23:21 AM · #4 |
Wow is right. I had no idea.
Can someone please provide a list of popular AI generative tools/engines? |
|
|
01/17/2025 10:23:41 AM · #5 |
I wouldn't have guessed posthumous would be the first to wade into this thread, but he did with both feet. Very interesting. |
|
|
01/17/2025 10:33:20 AM · #6 |
Originally posted by PennyStreet: Wow is right. I had no idea.
Can someone please provide a list of popular AI generative tools/engines? |
i don't have the list but this was done with a free chatGPT account. the only catch is that it limits the number of images i can create. |
|
|
01/17/2025 10:39:25 AM · #7 |
I should show this to my students. Distract them from using chatgpt to cheat lol.
Thanks for showing the chatgpt conversation. That was really helpful.
And that picture is beautiful! |
|
|
01/17/2025 10:55:05 AM · #8 |
I used chatGPT to create an image like the one I entered myself in the food photography challenge.
Can you create an image of falling colorful liquorice onto a table?
Here is the image of colorful liquorice candies falling onto a wooden table, capturing the playful and dynamic moment. Let me know if you'd like any adjustments!
You said:
I would like to see some slight movement in the image
Here is the updated image with a sense of motion added to depict the falling candies. Let me know if there's anything else you'd like to refine!
You said:
I would like to know how I can create such an image with a camera, i.e. which setting, lights and techniques to use.
ChatGPT said:
ChatGPT
Creating a visually dynamic image of falling colorful liquorice with a camera involves careful planning of lighting, camera settings, and techniques. Here's a guide:
The advice that followed was long and very generic, so I did not copy it here.
You said: More specifically, how do I get a sharp image of the liquorice at the lowest point with a streak of motion above it?
ChatGPT said:
ChatGPT
To capture a sharp image of the liquorice at its lowest point with a streak of motion above it, you need to combine a few specific techniques. Here's how you can achieve this:
Key Technique: Dragging the Shutter
Use a moderately slow shutter speed (e.g., 1/30 to 1/60 seconds) to capture motion blur.
Pair this with a burst of flash to freeze the liquorice at its lowest point.
and it added some more details to this advice
It did not make the "mental" change from capturing falling food to capturing food that is slowly moved upwards, like I did in my image, so I asked for it.
What if I use the flash first and then move the liquorice upwards?
ChatGPT said:
ChatGPT
Using a flash first and then moving the liquorice upwards can create a striking effect, but it involves some careful control. This approach would reverse the traditional motion streak direction (upwards instead of downwards), creating a unique image. Here's how to execute it:
Concept: Flash First, Upward Motion
The flash will freeze the liquorice in its starting position.
By moving the liquorice upwards immediately after the flash fires, you can create upward motion streaks captured by the camera's longer exposure.
Steps to Achieve This
I am leaving out some details ....
3. Liquorice Motion
After the flash fires, quickly pull the liquorice upwards with a consistent speed using a string, small rod, or by hand if feasible.
Ensure the motion is smooth to create clean, upward streaks.
4. Setup
Background: Use a dark or neutral background to make the motion streaks stand out.
Liquorice Holders: If you're holding the liquorice, use a string or fine support that can be removed or edited out in post-processing.
5. Shooting
Trigger the Flash: The flash should fire at the beginning of the exposure, freezing the liquorice in its initial position.
Move Liquorice Upwards: Start the upward motion immediately after the flash fires while the shutter remains open.
Practice Timing: Experiment with the timing and speed of the motion to get the desired length and clarity of the streaks.
6. Post-Processing
Edit Out Holders: Use Photoshop to remove strings or rods used to move the liquorice.
Enhance Streaks: Adjust brightness and contrast of the motion streaks for a more dramatic effect.
Sharpen the Liquorice: Apply selective sharpening to the flash-frozen liquorice to make it stand out.
Challenges and Tips
Control the Upward Motion: Ensure its smooth and straight to avoid chaotic streaks.
Avoid Overexposure: Keep ambient light low to prevent the liquorice from being overexposed during the motion.
Practice Timing: This technique may take several attempts to perfect, as timing the motion with the exposure is critical.
This setup offers an unconventional approach to motion photography, with the upward streak adding a unique visual twist to the image.
Message edited by author 2025-01-17 11:01:21. |
|
|
01/17/2025 11:10:19 AM · #9 |
Originally posted by posthumous: Originally posted by PennyStreet: Wow is right. I had no idea.
Can someone please provide a list of popular AI generative tools/engines? |
i don't have the list but this was done with a free chatGPT account. the only catch is that it limits the number of images i can create. |
But this is not in any way YOUR OWN image, correct? (sorry for being so naive but I want to be sure).
The result of your instructions is pretty spectacular though.
|
|
|
01/17/2025 01:37:53 PM · #10 |
Originally posted by PennyStreet: Originally posted by posthumous: Originally posted by PennyStreet: Wow is right. I had no idea.
Can someone please provide a list of popular AI generative tools/engines? |
i don't have the list but this was done with a free chatGPT account. the only catch is that it limits the number of images i can create. |
But this is not in any way YOUR OWN image, correct? (sorry for being so naive but I want to be sure).
The result of your instructions is pretty spectacular though. |
that's a great question. It does not remotely feel like my image. this is basically a technology designed to replace artists and photographers. in my opinion, there is no point "developing" this "talent" of prompting AI because nobody will pay you to do it. the whole point here is to not pay you, but to pay a big corporation instead. |
|
|
01/17/2025 02:23:30 PM · #11 |
Originally posted by posthumous: Originally posted by PennyStreet: Originally posted by posthumous: Originally posted by PennyStreet: Wow is right. I had no idea.
Can someone please provide a list of popular AI generative tools/engines? |
i don't have the list but this was done with a free chatGPT account. the only catch is that it limits the number of images i can create. |
But this is not in any way YOUR OWN image, correct? (sorry for being so naive but I want to be sure).
The result of your instructions is pretty spectacular though. |
that's a great question. It does not remotely feel like my image. this is basically a technology designed to replace artists and photographers. in my opinion, there is no point "developing" this "talent" of prompting AI because nobody will pay you to do it. the whole point here is to not pay you, but to pay a big corporation instead. |
And that's why I haven't paid it any attention. I'm not in this for the money but for the creativity. Telling someone else what to do would take the fun out of it, for me, even though the result is pretty.
Plus... where did they get those images? UGH. |
|
|
01/17/2025 02:28:00 PM · #12 |
Originally posted by PennyStreet: Plus... where did they get those images? UGH. |
the images are created. however, they do train on existing images. then again, you could say the same thing about any artist. |
|
|
01/17/2025 04:22:22 PM · #13 |
An interesting challenge would be to post an AI manufactured image and the challenge would be to post an image that either duplicates the AI image or is your interpretation of the image using your camera and extended editing. |
|
|
01/17/2025 05:41:49 PM · #14 |
Prompt:
Imagine three walruses lounging on a warm sandy beach in Trinidad & Tobago, their large, round bodies comfortably sprawled out beneath the soft hues of a tropical sunset. The sky glows in shades of orange, pink, and purple, as gentle waves lap against the shore. In front of the walruses, you can see tropical drinks colorful cocktails with little umbrellas nestled into the sand beside them, their tusks curiously nudging the drinks occasionally. Out in the distance, several luxurious superyachts are anchored just off the coast, their sleek white hulls reflecting the golden light of the setting sun. The scene is peaceful and surreal, an unexpected but serene blend of nature and opulence.
Modifiers:
highly detailed intricate Unreal Engine Michelangelo highly detailed highly detailed intricate highly detailed highly detailed highly detailed highly detailed
At some point this rather primitive approach de-tusked my walruses and killed one of them off then, in the description, changed them to Sea Lions, although they still look like walruses. "More about Sunset Bliss: Sea Lions and Luxury Yachts
Two sea lions lounge on a sandy beach, beside a colorful cocktail. In the background, a luxury yacht cruises in a serene sea under a vibrant sunset sky."
THis was done with the Deep Dream Generator
 |
|
|
01/17/2025 06:38:04 PM · #15 |
Ha. cross between sound and fury signifying nothing and not with a bang but with a whimper.
Vapid genius, A1.
Message edited by author 2025-01-17 19:56:11. |
|
|
01/17/2025 07:51:46 PM · #16 |
Its a Tool
Rule of Space
Deep dream generator
Model wearing a dress made of milk splashes in front of background consisting of an impressionistic, out-of-focus interior scene. The colors are dark, muted tones with a warm orange glow emanating from an unseen light source. The background is a blurry blend of dark browns and blacks, with slightly brighter, blurred shapes. Vertical streaks of lighter, desaturated colorsgrayish-white and light brownsimply depth. The impression is one of low light, creating a mysterious atmosphere. The perspective is from within the dimly lit space. The |
|
|
01/17/2025 08:25:32 PM · #17 |
Wow..
This blows me away, it's scary and magical at the same time. |
|
|
01/17/2025 11:24:13 PM · #18 |
backside challenge
Create a photograph of Mona Lisa from behind
ChatGPT said:
Here is an artistic interpretation of the Mona Lisa from behind, showcasing her seated posture and the Renaissance-style details. Let me know if you'd like any adjustments!
You said:
you are not behind her. the point of view should be from behind her looking at her back
ChatGPT said:
Here is the revised depiction of the Mona Lisa from behind, showing her back as she sits in her chair. Let me know if further adjustments are needed!
 |
|
|
01/18/2025 04:35:55 AM · #19 |
The Mona Lisa from behind is probably another example where there is insufficient training data available so it has difficulty producing the requested image. Apparently if you ask for an image of a watch showing a time where the hands are close together (for example 33 minutes past 6) it will shows a watch with hands 10 minutes past 10 since nearly all training images show that time.
|
|
|
01/18/2025 01:21:40 PM · #20 |
Originally posted by willem: The Mona Lisa from behind is probably another example where there is insufficient training data available so it has difficulty producing the requested image. Apparently if you ask for an image of a watch showing a time where the hands are close together (for example 33 minutes past 6) it will shows a watch with hands 10 minutes past 10 since nearly all training images show that time. |
it's funny to call it "insufficient training data." In reality,it shows there is no actual intelligence in artificial intelligence. Instead it is pattern recognition. So yes if there was infinite "training data" including conversations about photographing famous paintings from behind, then it might be able to do what I asked. |
|
|
01/20/2025 02:34:02 AM · #21 |
I am not interested in looking at shortcomings of AI, I could not paint Mona Lisa from the back either, what kind of test is this? What does it prove? Why not just have fun playing with ideas?? |
|
|
01/20/2025 11:09:02 AM · #22 |
Originally posted by MargaretNet: I am not interested in looking at shortcomings of AI, I could not paint Mona Lisa from the back either, what kind of test is this? What does it prove? Why not just have fun playing with ideas?? |
I am having fun. Why don't you start playing and contribute AI images to this thread? |
|
|
01/20/2025 11:24:49 AM · #23 |
You said:
create an image that is a macro photograph without bugs or flowers
ChatGPT said:
Here is a macro photograph focusing on natural textures and patterns, with intricate details and a soft, abstract aesthetic. Let me know if you'd like any adjustments!
You said:
Please zoom even further into the image, showing us even smaller structures in our natural world
ChatGPT said:
Here is an ultra-close macro photograph that reveals the minute, intricate structures of the natural world. Let me know if you'd like to explore further details or adjust the focus!
You said:
Please zoom even further and show hints of a whole other world within the tininess.
ChatGPT said:
Here is an extreme macro photograph that unveils a hidden, otherworldly landscape within the microscopic realm. Let me know if you'd like to explore this concept further!
 |
|
|
01/20/2025 11:53:14 AM · #24 |
Originally posted by posthumous: Originally posted by MargaretNet: I am not interested in looking at shortcomings of AI, I could not paint Mona Lisa from the back either, what kind of test is this? What does it prove? Why not just have fun playing with ideas?? |
I am having fun. Why don't you start playing and contribute AI images to this thread? |
To do that I would need to become a member again as I would need to upload images, putting them on my Website and linking is a nuisance. I would be very interested to see output of multiple AI generation sites with the same prompts but if it is just the two of us contributing it will be very limited.
Doesn't anyone else want to contribute and play with AI? |
|
|
01/20/2025 11:58:00 AM · #25 |
|
Home -
Challenges -
Community -
League -
Photos -
Cameras -
Lenses -
Learn -
Help -
Terms of Use -
Privacy -
Top ^
DPChallenge, and website content and design, Copyright © 2001-2025 Challenging Technologies, LLC.
All digital photo copyrights belong to the photographers and may not be used without permission.
Current Server Time: 03/30/2025 11:40:13 PM EDT.