Imágenes generadas por IA de foreros

[Lovekraft]

Muy bien, @Lovekraft

Me gusta la idea, voy a ver qué aproximación consigo con mi técnica con la IA.

Ánimo y a seguir compartiendo.

si, molaria pulirlo más pero no tengo tiempo... basicamente es pillar un poster hiperreconocible e intentar reinterpretarlo bajo la optica de un pintor o artista famoso.

 

[Lovekraft]

Los duelistas como si fuera un cuadro de Caspar David Friedrich (uno de mis pintores favoritos)

 

[DeBilbao]

Se me ocurre que podríamos plantear que los carteles estén colgados en una exposición temporal de un museo, como si fuesen cuadros.

También se podría plantear como creaciones de Banksy

Y si nos venimos arriba, podría ser una creación alternativa de Banksy, cubriendo la fachada de un edificio, con una versión alternativa del clásico Tiempos Modernos con una crítica a los tiempos modernos que vivimos...

 

[DeBilbao]

Esto de generar posters, engancha.

Os comparto algunos intentos de versiones alternativas, más o menos afortunados.

 

[DeBilbao]

Deepseek no es capaz de interpretar el contenido de una imagen, así que si quiero "inspirarme" en una imagen ya existente, tengo que buscarme otra IA que lo haga.

Por ejemplo, a Google Gemini y su modelo Flash 2.5 le puedes pedir que te interprete una imagen como este poster de la película "El ataque de la mujer de 50 pies".

Si me llevo ese texto directamente a ImageFX, obtengo resultados bastante aceptables (aunque le ha puesto unas patorras que ni a Hulk).

He intentado probar otra receta con Grok, que me permite subirle una imagen y le puedo pedir que cree una versión de la misma respetando la imagen y presentando a la protagonista como una mujer gigante y atractiva, que se dedica a recoger coches de la carretera.

En lugar de un coche, ha interpretado que en sus manos tenía un arma, así que le he pedido que corrija.

Y ahí se le ha ido la pinza...

​

 

[DeBilbao]

Las capacidades de ImageFX están a otro nivel.

Os pongo un ejemplo, simplemente seleccionando el comentario que hacen sobre la película The Rocketeer en esta web que recoje 50 posters icónicos.

The 50 Best Movie Posters Ever

Some posters are as iconic as the films they're promoting. See Empire's list of the best film posters ever.

www.empireonline.com

Fijaos lo qu ees capaz de generar simplemente con esa descripción.

 

[DeBilbao]

Repito el ejercicio de interpretación de imagen con Desayuno con Diamantes.

Se lo doy a Google Gemini (Flash 2.5) para que lo interprete

Y le pido a ImageFX que lo genere "tal cual" a partir de esa espectacular descripción

This is a movie poster for the iconic film "Breakfast at Tiffany's." The poster features a striking and elegant illustration with a clean, stylized design.

The dominant figure is a full-body illustration of actress Audrey Hepburn, portraying her famous role as Holly Golightly. She is depicted in her classic little black dress, a form-fitting gown with a slit up the left leg. She wears long black gloves that extend past her elbows. Her hair is styled in an elaborate updo, and she is wearing a tiara, prominent pearl earrings, and a pearl necklace. She has a dramatic makeup look with winged eyeliner.

Hepburn is shown holding a long cigarette holder in her right hand, with a cigarette at the end, which she is raising towards her mouth. Her left hand is resting on her hip. She is standing in a graceful, slightly turned pose with one foot slightly forward.

The background is predominantly a bright, stark white, which makes the figure of Hepburn stand out prominently. On the right side of the poster, there is a smaller illustration featuring two figures embracing in front of abstract representations of pink and grey buildings, presumably depicting a scene or romantic element from the film.

Below the central figure and to the right, the title "AUDREY HEPBURN" is printed in large black capital letters. Below her name, there is text in smaller font reading "PLAYS THAT DARING, DARLING HOLLY GOLIGHTLY TO A NEW HIGH IN ENTERTAINMENT DELIGHT!". The main title, "BREAKFAST AT TIFFANY'S," is displayed in large, stylized pink lettering with a slight shadow effect, positioned below the descriptive text. The "AT" is in smaller text nestled within "BREAKFAST."

At the very bottom of the poster, in a band of orange/yellow, are the names of other cast members (GEORGE PEPPARD, NEAL EBSEN, BALSAM, MICKEY ROONEY) and "TECHNICOLOR," indicating the film's color format. There are also smaller credits below this band.

The left side of the poster features a bold vertical red stripe, and the right side has a similar vertical blue stripe, adding blocks of color to the overall composition. The top of the poster has horizontal bands of yellow and light green.

The overall aesthetic is sophisticated and stylish, using clean lines and bold blocks of color to create a memorable and iconic image that perfectly represents the film's blend of glamour and romantic comedy.

 

[DeBilbao]

Si le digo a DeepSeek que le voy a dar esa descripción y que quiero que me cree una nueva imagen más actualizada y refinada, se pone a mi disposición:

Y ImageFX cumple con su tarea

El resultado nos puede convencer más o menos que el anterior, pero entendéis la idea y lo potente del método ¿no?

 

[DeBilbao]

Una vez tenemos la churrera en marcha, es tan sencillo como:

Elegir una película, como por ejemplo Planeta Prohibido, y descargar su poster de FilmAffinity

Pedirle a Google Gemini que nos analice el poster

Pedirle a DeepSeek que nos cree una versión más modderna y actualizada del texto

Pedirle a Google ImageFX que nos cree la nueva imagen.

En este caso, yo diría que el original supera a la actualización

 

[DeBilbao]

Una vez la churrera en marcha, pasar del original a la actualización es cuestión de minutos.

Del original

A la versión actualizada, que en este caso no me gusta mucho con esa interpretación de que lo que se llevó el viento fueron los billetes...

Pero nada que no puedas resolver al instante, pidiéndole a DeepSeek que te de una nueva versión, sin eso que te molesta, más fotorealista y que permita identificar a Clark Gable y a Vivien Leigh sin problemas.

 

[Carlos_C]

Bueno, pues aquí dejo mi imagen de "fantasmas", lo mejor que conseguí yo. Una niña en un cementerio no es muy común pero aún así no me parece muy fantasmal:



Y luego un par de la serie "Patinetes eléctricos y Charos":

 

[DeBilbao]

Bueno, pues aquí dejo mi imagen de "fantasmas", lo mejor que conseguí yo. Una niña en un cementerio no es muy común pero aún así no me parece muy fantasmal:

Y luego un par de la serie "Patinetes eléctricos y Charos":

Todo suma, y de todo aprendemos

Eso sí, lo de las "Charos" no me resulta atractivo ¿eh?

 

[DeBilbao]

Otro ejercicio, con 3 versiones que no consiguen superar al original...

Original

Versión 1

Versión 2

Versión 3

 

[DeBilbao]

Esta, con cariño para @King Conan

 

[Lovekraft]

me sale un resultado parecido pero no se acerca al original ni de blas, en calidad e impacto...

 

[DeBilbao]

He realizado un nuevo intento, pidiéndole a Gemini que describa lo que ve como si alguien se lo tuviera que contar a una persona ciega.

Y algo mejora, pero no sale de la forma en la que hemos conseguido los resultados.

DeepSeek me da un consejo, por si alguien quiere buscar...

"For complete accuracy, cross-reference with the 1982 Style B one-sheet poster (NSS #82148), particularly for:

Exact text placement and font styles

The specific hue of the sky's purple-red gradient

The precise angle of Conan's sword relative to his body

Valeria's exact boot design and armor stitching pattern"

 

[Lovekraft]

lo curioso es que si le pides que te enseñe el poster original te lo encuentra y te lo manda pero en cuanto le pides que te lo reinterprete manteniendo las mismas posturas, personajes, fondos...lo manda todo a la mierda y te hace algo diferente. Curioso como piensa la maquina...

Eso si, si les pides que te lo describan lo clavan

• Central Figure: Conan dominates the composition, standing tall and muscular, embodying raw power. He’s depicted with long, dark hair and a fierce expression, gripping a massive, double-edged sword raised above his head with both hands. His physique is exaggeratedly chiseled, emphasizing his barbaric strength.
• Pose and Stance: Conan stands atop a rocky outcrop or pile of skulls, exuding dominance over a chaotic battlefield. His stance is wide and commanding, with one foot forward, suggesting readiness for combat. His body is slightly turned, showcasing his broad shoulders and defined muscles.
• Attire and Gear: He wears minimal clothing—a loincloth or fur kilt, with a belt adorned with pouches or a dagger. His arms are bare except for wristbands or bracers, and he sometimes has a necklace with a pendant. The lack of armor highlights his reliance on brute strength.
• Background and Setting: The scene is dark and gritty, set against a misty, volcanic landscape with jagged rocks and a blood-red sky. Fallen warriors and broken weapons litter the ground, hinting at a recent, brutal battle. The atmosphere is primal, with a sense of untamed wilderness.
• Female Companion: At Conan’s side, often clinging to his leg or standing close, is a scantily clad woman—likely Valeria, a key character from the film. She’s depicted with flowing hair, wearing a revealing outfit, and holding a sword or dagger, suggesting she’s a warrior in her own right but subordinate to Conan’s dominance.
• Color Palette: The poster uses bold, contrasting colors—deep blacks, fiery reds, and earthy browns. Conan’s skin is bronzed, standing out against the darker background. The red sky and glowing highlights on his sword add drama and intensity.
• Art Style: Frazetta’s signature style is evident—hyper-realistic yet fantastical, with dynamic composition and a focus on movement. The brushwork is textured, giving the figures a visceral, almost three-dimensional quality.
• Text and Layout: The title “Conan the Barbarian” is typically in bold, blocky letters at the bottom or top, often in white or gold to stand out. Additional text, like the tagline (“Thief. Warrior. Gladiator. King.”) or credits, is minimal and placed unobtrusively. The focus remains on the central image.

 

[Lovekraft]

en otro orden de cosas y aqui es más facil generar imagenes que nos gusten, le pedi que me enseñará la imagen de lo que podriamos ver justo después del Big Bang...

 

[Tiberiuz]

Con estrellas de fondo???

 

[Lovekraft]

Con estrellas de fondo???

si la IA es mu creativa...

 

[Insidius]

Cabron de chatgpt. Le subo una foto de dos colegas, de digo que me haga una caricatura y no hay manera.

Primero le he pedido estilo mortadelo y filemon, pero no hay manera, que sus políticas lo prohiben

 

[Lovekraft]

Cabron de chatgpt. Le subo una foto de dos colegas, de digo que me haga una caricatura y no hay manera.

Primero le he pedido estilo mortadelo y filemon, pero no hay manera, que sus políticas lo prohiben

has probado alguna pagina asi

Photo to cartoon AI - AI turn photo into cartoon free online

Explore the world of AI Cartoonizer tools and discover how they transform ordinary photos into captivating cartoons effortlessly.

cartoonizer.ai

 

[DeBilbao]

Cabron de chatgpt. Le subo una foto de dos colegas, de digo que me haga una caricatura y no hay manera.

Primero le he pedido estilo mortadelo y filemon, pero no hay manera, que sus políticas lo prohiben

¿Y por qué no pruebas la receta que os compartía ayer?

Por ejemplo, usando esta foto de stock de una pareja:

Le he dicho a Google Gemini que la describa con precisión y me ha generado esto:

This image shows a head-and-shoulders portrait of a smiling couple against a plain white background.

The man is in the foreground, slightly to the left. He has short brown hair and a beard. He is wearing a blue, white, and red plaid shirt. He is facing forward, looking directly at the camera with a wide, genuine smile, showing his teeth. His arms are crossed over his chest.

The woman is positioned behind the man, her head resting near his right shoulder. She has long, wavy brown hair and is also smiling broadly, looking at the camera. She is wearing a light-colored, long-sleeved top, likely white or cream. Her right arm is around the man's neck, and her left hand is resting on his left arm.

Both individuals appear happy and relaxed, with a warm and joyful expression. The lighting is even, suggesting a studio setting. The white background helps to focus attention entirely on the couple.

Si lo uso tal cual como un prompt en ImageFX, el resultado no es idéntico, pero se aproxima a la realidad.

Si le digo a DeepSeek que me haga una descripción de ese texto en formato caricatura, me dice esto:

This image is a bright, cheerful cartoon portrait of a smiling couple against a crisp white background, drawn in a lively, animated style.
The man is front and center, slightly to the left, with playful, spiky brown hair and a neatly trimmed beard. He’s wearing a bold, colorful plaid shirt in blue, white, and red, with exaggerated checks for a fun, cartoony look. His arms are crossed in a confident pose, and he’s beaming a huge, toothy grin straight at the viewer, his eyes sparkling with joy.
Peeking over his right shoulder is the woman, her long, bouncy brown hair cascading in loose waves. She’s also grinning widely, her eyes crinkled with happiness. She wears a soft, light-colored long-sleeved top—maybe cream or pastel—with gentle folds to give it a cozy feel. One arm is draped warmly around the man’s neck, while her other hand rests playfully on his arm.
Both characters have exaggerated, expressive smiles and bright, shining eyes, radiating warmth and fun. The clean white backdrop keeps all the focus on their vibrant, cartoonish charm, making them look like they’ve stepped right out of a heartwarming animated series!

Y lo uso directamente como prompt, tengo unas caricaturas

 

[DeBilbao]

Otro ejemplo para demostrar que la técnica funciona, y más con personajes conocidos.

Son 3 IAs distintas, pero el proceso completo te lleva un par de minutos, no más.

Partiendo de este retrato de Laurel y Hardy

Gemini interpreta esto:

This image is a colorized portrait of the famous comedy duo Laurel and Hardy, posed against a solid red background.

On the left is Stan Laurel. He is wearing a light brown suit jacket with wide lapels, a white dress shirt, and a red and white polka dot bowtie. A pink or red pocket square is visible in his jacket pocket. He is wearing his signature small black bowler hat positioned squarely on his head. He has a sheepish or slightly awkward smile on his face and is looking off to the left side of the frame with a slightly upward gaze.

On the right is Oliver Hardy. He is larger in stature than Laurel. He is wearing a blue suit jacket, a white dress shirt, and a dark blue tie with white polka dots. His black bowler hat is perched on the back of his head. He has his characteristic expression of frustration or exasperation, with furrowed brows and a downturned mouth, and is looking upwards and slightly to the right.

The two comedians are standing side-by-side, framed from the chest up. The red background provides a stark contrast to their clothing and skin tones.

ImageFX crea esto con ese prompt, que se podría mejorar ajustándolo, pero he preferido dejarlo "tal cual".

DeepSeek me hace este prompt alternativo para caricatura:

This image is a vibrant, exaggerated cartoon portrait of the legendary comedy duo Laurel and Hardy, popping against a bold, solid red background—like a classic animated poster!

On the left, Stan Laurel is drawn with his iconic lanky frame and goofy charm. He wears a light brown suit jacket with comically wide lapels, a crisp white dress shirt, and a whimsical red-and-white polka-dot bowtie that bounces with energy. A flamboyant pink pocket square pokes out from his jacket like a little flag of silliness. His tiny black bowler hat sits perfectly straight on his head, almost too small, adding to his lovable klutziness. His face has a sheepish, slightly clueless grin, eyes glancing off to the side with an upward gaze, as if he’s just accidentally broken something (again).

On the right, Oliver Hardy looms large, his round belly and double chin exaggerated for maximum cartoonish grumpiness. He’s stuffed into a snug blue suit jacket, his white shirt straining slightly under his wide polka-dotted tie. His black bowler hat perches precariously on the back of his head, as if it might tip off any second. His face is a masterpiece of cartoon frustration—bushy eyebrows scrunched together, cheeks puffed, and mouth turned down in his classic "Well, here’s another nice mess you’ve gotten me into!" expression. His eyes roll dramatically upward, as if begging the heavens for patience.

The two stand side-by-side, their contrasting expressions and body language making them the perfect cartoon comedy pair. The bright red background makes their outfits and exaggerated features pop like a classic Looney Tunes cel, full of energy and timeless humor!

Que ImageFX interpreta bastante bien:

 

[Tiberiuz]

Pues con tu receta particular da un resultado bastante parecido a lo que pedía @Insidius

Con la foto inicial de @DeBilbao



Y este prompt en Chat GPT

Me puedes hacer una caricatura de estas dos personas con el estilo de Francisco Ibáñez, el dibujante español?