theally

    Showing 273 posts by theally

    🎬
    Video
    Flux.1 D

    The skull-shaped drink slowly begins to move, its jaw subtly shifting before breaking into a wide, eerie laugh. The ice inside rattles slightly with each motion. The straw wobbles gently as the laughter echoes. The surrounding palm leaves sway lightly in the breeze, and ocean waves roll in the background. The movement is smooth and natural, enhancing the surreal atmosphere.

    6019 likes
    🎬
    Video

    a happy cocktail, singing on a tropical beach

    5796 likes
    🖼️
    Flux Pro 1.1 available on the Civitai Image Generator now!
    Flux.1 D

    Flux Pro 1.1 available on the Civitai Image Generator now!

    5744 likes
    🖼️
    Exterior view of a Victorian-style Milliner shop with a wooden sign, with a selection of hats in the window. A victorian man wearing a very large top hat stands proudly at the door. A banner is draped across the wall saying ("Hatters will say this is AI":1.25), whimsical, funny, illustration

    Exterior view of a Victorian-style Milliner shop with a wooden sign, with a selection of hats in the window. A victorian man wearing a very large top hat stands proudly at the door. A banner is draped across the wall saying ("Hatters will say this is AI":1.25), whimsical, funny, illustration

    4749 likes
    🖼️
    Upscale from Civitai Generator

    Upscale from Civitai Generator

    4698 likes
    🖼️
    text "Train Flux on Civitai" in colorful graffiti written on the side of a train wagon

    text "Train Flux on Civitai" in colorful graffiti written on the side of a train wagon

    4598 likes
    🎬
    Video
    OpenAI

    The turtle (The Great God Om), dropped by the eagle, falls through the air, clouds rushing past, screaming, arms and legs flailing

    4568 likes
    🖼️
    Nano Banana
    3732 likes
    🖼️
    Nano Banana
    3700 likes
    🎬
    Video
    Flux.1 D

    water flowing out of an enchanted gateway mirror, portal to another world, desert sand flying in the desolate wind, lush verdant landscape inside the mirror

    3617 likes
    🎬
    Video
    3024 likes
    🎬
    Video
    Mochi

    a first person drone shot flying over the rugged mountains and rolling hills of the Scottish landscape at speed

    2887 likes
    🖼️
    A beautiful realistic image from a miniature perspective, tiny tiny man, among blades of grass, looking up at a gigantic looming lawnmower, emphasizing the size difference, foreshortening style, a horror-esque image of the man in a panic as the lawnmower bears down upon him, from behind his back
    OpenAI

    A beautiful realistic image from a miniature perspective, tiny tiny man, among blades of grass, looking up at a gigantic looming lawnmower, emphasizing the size difference, foreshortening style, a horror-esque image of the man in a panic as the lawnmower bears down upon him, from behind his back

    1292 likes
    🎬
    Video
    Mochi

    award winning closeup portrait photo of an polynesian woman, water goddess, body tattoos, wading in the pacific ocean, partially submerged shot, style-moana, trending on artstation, highly detailed, fine detail, intricate, lens flare, backlighting, bloom

    1208 likes
    🖼️
    An infographic style announcement saying "We've added a quality selector! Medium quality now 100 Buzz ⚡"
    OpenAI

    An infographic style announcement saying "We've added a quality selector! Medium quality now 100 Buzz ⚡"

    686 likes
    🖼️
    A wide image taken with a phone of a glass whiteboard, in a room overlooking the Bay Bridge. The field of view shows a woman writing, sporting a tshirt wiith a large OpenAI logo. The handwriting looks natural and a bit messy, and we see the photographer's reflection.

The text reads:

(left)
"Transfer between Modalities:

Suppose we directly model
p(text, pixels, sound) [equation]
with one big autoregressive transformer.

Pros:
* image generation augmented with vast world knowledge
* next-level text rendering
* native in-context learning
* unified post-training stack

Cons:
* varying bit-rate across modalities
* compute not adaptive"

(Right)
"Fixes:
* model compressed representations
* compose autoregressive prior with a powerful decoder"

On the bottom right of the board, she draws a diagram:
"tokens -> [transformer] -> [diffusion] -> pixels"
    OpenAI

    A wide image taken with a phone of a glass whiteboard, in a room overlooking the Bay Bridge. The field of view shows a woman writing, sporting a tshirt wiith a large OpenAI logo. The handwriting looks natural and a bit messy, and we see the photographer's reflection. The text reads: (left) "Transfer between Modalities: Suppose we directly model p(text, pixels, sound) [equation] with one big autoregressive transformer. Pros: * image generation augmented with vast world knowledge * next-level text rendering * native in-context learning * unified post-training stack Cons: * varying bit-rate across modalities * compute not adaptive" (Right) "Fixes: * model compressed representations * compose autoregressive prior with a powerful decoder" On the bottom right of the board, she draws a diagram: "tokens -> [transformer] -> [diffusion] -> pixels"

    575 likes
    🖼️
    sd3grl, Girl Lying on Grass <lora:SD3_Girl_Lying_on_Grass:1>
    SDXL 1.0

    sd3grl, Girl Lying on Grass <lora:SD3_Girl_Lying_on_Grass:1>

    549 likes
    🖼️
    selfie view of the photographer, as she turns around to high five him
    OpenAI

    selfie view of the photographer, as she turns around to high five him

    451 likes
    🖼️
    A cat looking into a puddle of water on a street, but its reflection is that of a tiger, and both reflections are realistically distorted by ripples in the water
    OpenAI

    A cat looking into a puddle of water on a street, but its reflection is that of a tiger, and both reflections are realistically distorted by ripples in the water

    427 likes
    🎬
    Video
    SD 1.5
    424 likes
    🎬
    Video

    masterpiece, highly detailed, realistic, lakeside, beside a lake, foliage, forest, (standing on a wooden pier:1.4), 1girl cute, kawaii, (full body:1.3), (chibi:1.3), (brat:1.1), chubby, thicc, thick, (sun dress:1.6), detailed, smug, red hair, (side ponytail:1.1), small breasts, (sparkling eyes:1.1), (swiss mountains:1.4), happy, laughing, (light sparkles:1.3), (lens flare:1.3), (shallow depth of field:1.5) <lora:more_details:1>, by lee jeffries nikon d850 film stock photograph 4 kodak portra 400 camera f1.6 lens rich colors hyper realistic lifelike texture dramatic lighting unrealengine trending on artstation cinestill 800, (Extremely Detailed Oil Painting:1.2), glow effects, godrays, Hand drawn, render, 8k, octane render, cinema 4d, blender, dark, atmospheric 4k ultra detailed, cinematic sensual, Sharp focus, humorous illustration, big depth of field, Masterpiece, colors, 3d octane render, 4k, concept art, trending on artstation, hyperrealistic, Vivid colors, extremely detailed CG unity 8k wallpaper, trending on ArtStation, trending on CGSociety, Intricate, High Detail, dramatic

    407 likes
    🖼️
    Create a photorealistic image of two witches in their 20s (one ash balayage, one with long wavy auburn hair) reading a street sign.

Context:
a city street in a random street in Williamsburg, NY with a pole covered entirely by numerous detailed street signs (e.g., street sweeping hours, parking permits required, vehicle classifications, towing rules), including few ridiculous signs at the middle: (paraphrase it to make these legitimate street signs)"Broom Parking for Witches Not Permitted in Zone C" and "Magic Carpet Loading and Unloading Only (15-Minute Limit)" and "Reindeer Parking by Permit Only (Dec 24–25)\n Violators will be placed on Naughty List." The signpost is on the right of a street. Do not repeat signs. Signs must be realistic.

Characters:
one witch is holding a broom and the other has a rolled-up magic carpet. They are in the foreground, back slightly turned towards the camera and head slightly tilted as they scrutinize the signs.

Composition from background to foreground:
streets + parked cars + buildings -> street sign -> witches. Characters must be closest to the camera taking the shot
    OpenAI

    Create a photorealistic image of two witches in their 20s (one ash balayage, one with long wavy auburn hair) reading a street sign. Context: a city street in a random street in Williamsburg, NY with a pole covered entirely by numerous detailed street signs (e.g., street sweeping hours, parking permits required, vehicle classifications, towing rules), including few ridiculous signs at the middle: (paraphrase it to make these legitimate street signs)"Broom Parking for Witches Not Permitted in Zone C" and "Magic Carpet Loading and Unloading Only (15-Minute Limit)" and "Reindeer Parking by Permit Only (Dec 24–25)\n Violators will be placed on Naughty List." The signpost is on the right of a street. Do not repeat signs. Signs must be realistic. Characters: one witch is holding a broom and the other has a rolled-up magic carpet. They are in the foreground, back slightly turned towards the camera and head slightly tilted as they scrutinize the signs. Composition from background to foreground: streets + parked cars + buildings -> street sign -> witches. Characters must be closest to the camera taking the shot

    393 likes
    🎬
    Video
    OpenAI

    A warrior mouse riding on a pig, galloping into battle

    391 likes
    🖼️
    An official looking declaration scroll pinned to a wooden door, medieval, text "Truth, Justice, Freedom, Reasonably Priced Love, and a Hard-Boiled Egg", "People's Republic of Treacle Mine Road", a sprig of lilac flower in the foreground
    OpenAI

    An official looking declaration scroll pinned to a wooden door, medieval, text "Truth, Justice, Freedom, Reasonably Priced Love, and a Hard-Boiled Egg", "People's Republic of Treacle Mine Road", a sprig of lilac flower in the foreground

    387 likes
    🖼️
    A realistic underwater scene with dolphins swimming through the windows of an abandoned subway car, with bubbles and detailed water flow accurately simulated.
    OpenAI

    A realistic underwater scene with dolphins swimming through the windows of an abandoned subway car, with bubbles and detailed water flow accurately simulated.

    354 likes
    🎬
    Video
    339 likes
    🖼️
    make a visual infographic describing why SF is so foggy
    OpenAI

    make a visual infographic describing why SF is so foggy

    323 likes
    🖼️
    OpenAI
    317 likes
    🖼️
    create an educational poster of different types of whales in an effervescent watercolor style. make the background pure white.
    OpenAI

    create an educational poster of different types of whales in an effervescent watercolor style. make the background pure white.

    309 likes
    🖼️
    Realistic photograph of a horse galloping from right to left across a vast, calm ocean surface, accurately depicting splashes, reflections, and subtle ripple patterns beneath their hooves. Exaggerate horse movements but everything else should be still, quiet to show contrast with the horse's strength. clean composition, cinematographic. A wide, panoramic composition showcasing a distant horizon. Atmospheric perspective creating depth. zoomed out so the horse appears minuscule compared to vast ocean.

horse is right at the horizon where ocean meets sky. use rule of thirds to position horse. size of horse is 1% size of entire image because camera is so far away from subject. camera view is super close to the ground/ocean like a worm's eye view. horse is galloping right where ocean meets the sky
    OpenAI

    Realistic photograph of a horse galloping from right to left across a vast, calm ocean surface, accurately depicting splashes, reflections, and subtle ripple patterns beneath their hooves. Exaggerate horse movements but everything else should be still, quiet to show contrast with the horse's strength. clean composition, cinematographic. A wide, panoramic composition showcasing a distant horizon. Atmospheric perspective creating depth. zoomed out so the horse appears minuscule compared to vast ocean. horse is right at the horizon where ocean meets sky. use rule of thirds to position horse. size of horse is 1% size of entire image because camera is so far away from subject. camera view is super close to the ground/ocean like a worm's eye view. horse is galloping right where ocean meets the sky

    299 likes
    🖼️
    A square image containing a 4 row by 4 column grid containing 16 objects on a white background. Go from left to right, top to bottom. Here's the list:
1. a blue star
2. red triangle
3. green square
4. pink circle
5. orange hourglass
6. purple infinity sign
7. black and white polka dot bowtie
8. tiedye "42"
9. an orange cat wearing a black baseball cap
10. a map with a treasure chest
11. a pair of googly eyes
12. a thumbs up emoji
13. a pair of scissors
14. a blue and white giraffe
15. the word "OpenAI" written in cursive
16. a rainbow-colored lightning bolt
    OpenAI

    A square image containing a 4 row by 4 column grid containing 16 objects on a white background. Go from left to right, top to bottom. Here's the list: 1. a blue star 2. red triangle 3. green square 4. pink circle 5. orange hourglass 6. purple infinity sign 7. black and white polka dot bowtie 8. tiedye "42" 9. an orange cat wearing a black baseball cap 10. a map with a treasure chest 11. a pair of googly eyes 12. a thumbs up emoji 13. a pair of scissors 14. a blue and white giraffe 15. the word "OpenAI" written in cursive 16. a rainbow-colored lightning bolt

    298 likes
    🖼️
    OpenAI
    268 likes
    🎬
    Video
    258 likes
    🖼️
    A hyper-realistic image with a miniature perspective: a tiny, stunned man balances precariously on a wet bar of soap floating in a sink full of suds. He looks panicked and confused, clutching the slippery surface as waves of foam rise around him. A massive faucet looms in the background, with water droplets the size of basketballs threatening to splash down. The lighting is bright and clinical, like a bathroom. Shallow depth of field enhances the dramatic scale difference. Comical and chaotic energy, with a slight tilt to the scene as the soap begins to rotate.
    OpenAI

    A hyper-realistic image with a miniature perspective: a tiny, stunned man balances precariously on a wet bar of soap floating in a sink full of suds. He looks panicked and confused, clutching the slippery surface as waves of foam rise around him. A massive faucet looms in the background, with water droplets the size of basketballs threatening to splash down. The lighting is bright and clinical, like a bathroom. Shallow depth of field enhances the dramatic scale difference. Comical and chaotic energy, with a slight tilt to the scene as the soap begins to rotate.

    257 likes
    🖼️
    an infographic explaining newton's prism experiment in great detail
    OpenAI

    an infographic explaining newton's prism experiment in great detail

    255 likes
    🖼️
    Make me a professionally shot photorealistic diagram of the top selling cocktails in my bar with recipes labeled on each drink.

put the recipes on handwritten cards in front of each drink.

the cards are brown, and the text is black.

background is white

Title is "4 most popular cocktails"
    OpenAI

    Make me a professionally shot photorealistic diagram of the top selling cocktails in my bar with recipes labeled on each drink. put the recipes on handwritten cards in front of each drink. the cards are brown, and the text is black. background is white Title is "4 most popular cocktails"

    248 likes
    🖼️
    sd3grl, Girl Lying on Grass <lora:SD3_Girl_Lying_on_Grass:1>
    SDXL 1.0

    sd3grl, Girl Lying on Grass <lora:SD3_Girl_Lying_on_Grass:1>

    245 likes
    🖼️
    product photography, a box of "Civitai Porridge Oats", overlooking the beautiful Scottish highlands, pine forest and snow covered hills in distance, sunrise, cinematic

    product photography, a box of "Civitai Porridge Oats", overlooking the beautiful Scottish highlands, pine forest and snow covered hills in distance, sunrise, cinematic

    243 likes
    🖼️
    now generate a POV of a person drawing this diagram in their notebook, at a round cafe table in washington square park
    OpenAI

    now generate a POV of a person drawing this diagram in their notebook, at a round cafe table in washington square park

    238 likes
    🖼️
    SD 3
    236 likes
    🖼️
    SD 3
    228 likes
    🖼️
    in the style of snek, a mallard duck with the text "throw bread on me" underneath
    Flux.1 D

    in the style of snek, a mallard duck with the text "throw bread on me" underneath

    227 likes
    🎬
    Video
    SD 1.5
    224 likes
    🖼️
    SD 3
    212 likes
    🖼️
    SD 3.5
    212 likes
    🎬
    Video
    OpenAI

    a forest dryad, coy, smiling, looking around

    210 likes
    🖼️
    209 likes
    🖼️
    sd3grl, Girl Lying on Grass <lora:SD3_Girl_Lying_on_Grass:1>
    SDXL 1.0

    sd3grl, Girl Lying on Grass <lora:SD3_Girl_Lying_on_Grass:1>

    204 likes
    🎬
    Video
    OpenAI

    detailed realistic portrait photo of a slim sexy toned female bard with long flowing red hair, cleavage, thigh slit, on a wooden stage in a candle lit tavern, singing and playing a lute to silhouettes of an adoring audience in the foreground. She wears brightly colored bard clothing and seems happy and joyful. The scene is cinematic, with a realistic cold blue light hue, but reminiscent of a fantasy portrait

    204 likes
    🎬
    Video
    SD 1.5
    183 likes