
FLUX 3 Poster & Typography Prompts
400 FLUX 3 image prompts that people published with their images: on Civitai under the base models Flux.3, Flux.3 Klein and Flux.3 Klein-base, and on X. Each one is quoted in full, word for word, credited to its author and linked to the original post, next to the image it produced. We did not write any of them, and apimodels.app does not offer a FLUX 3 image model.
Last updated: · Models we run · API docs
TL;DR
FLUX 3 is Black Forest Labs' image model line, and on Civitai its images are posted under three base-model labels: Flux.3, Flux.3 Klein and Flux.3 Klein-base. This page collects 400 prompts that people published with their FLUX 3 images there and on X, each with the image it produced and a link to the source. apimodels.app does not offer a FLUX 3 image model, so these prompts cannot be run as images through our API. FLUX 3 Max on apimodels.app is a different product: a video model, a variant of FLUX 3 Video, that turns a prompt, a first frame or up to 10 timed keyframes into a 5 to 20 second clip with sound, from $0.221 per second, and a still made from one of these prompts can serve as its first frame. A Civitai image also depends on settings that are not in the prompt, such as the seed, sampler, step count and size, so the same words will not reproduce the same picture. Civitai posts whose generation data lists a LoRA are left out.
Source: Black Forest Labs FLUX 3 (the model vendor’s official site)


Retro-Futurist Mountain Travel Poster
Retro-futurist travel poster reading "FLUX.3 KLEIN" in bold geometric letters above a stylized mountain range at sunset, flat colors, screen-print texture

Letterpress Poster Workshop
{"rewritten_prompt": "The image is a square, photorealistic documentary photograph of a freshly printed cream paper poster in a traditional letterpress workshop, photographed from very close range so that the poster fills the left four-fifths of the frame and its upper-left corner coincides exactly with the upper-left corner of the image. The poster's left, top and bottom edges run right to the edges of the frame, while its right edge is fully visible at about four-fifths of the image width, held taut by a young adult woman. The thick ivory paper has a tactile, slightly rough surface, visible fibres and softly irregular deckled edges along its right side. Subtle Chinese-inspired armament motifs are debossed directly into the paper, creating delicate recessed impressions with no ink, pigment or added colour. The tone-on-tone relief depicts traditional Chinese polearms, crossed dao sabres, spearheads, arrowheads, ornate guard shapes and cloud-patterned fittings, arranged as a restrained decorative border and faint ornamental compositions in the empty areas around the lettering, visible only through shallow grooves and soft grazing shadows, and never overlapping the text. In the extreme upper-left corner of the poster, set in a small even margin of paper from the frame's top and left edges, a large rectangular blue outline encloses the exact characters \"5.6B\" in bold blue serif capitals, the box about one-eighth of the image width and fully visible. Across the middle of the poster, the exact headline \"FLUX.3 Image\" appears on the first line in very large, heavy, black serif capitals that span nearly the full width of the poster, and the exact text \"Klein\" appears centred on a second line below it in the same heavy black style at an even larger size. The lettering has slightly uneven ink coverage and an authentic raised letterpress texture, with crisp edges, correct spelling and clear separation from the debossed ornamentation. Near the lower centre of the sheet, the word \"Black Forest Labs\" appears in small black italic lettering. On the right side of the frame, the young adult woman stands slightly turned toward the poster with her face at about the vertical middle of the image, with short black hair and a calm, satisfied expression, holding the poster's right edge with ink-stained fingers. She wears a loosely rolled white shirt beneath a dark indigo canvas apron. Behind her, softly blurred wooden type drawers, small ink tins and the worn flywheel of a vintage black cast-iron letterpress establish the print-shop setting, while a pale, plain window glow fills the upper-right corner of the frame. A narrow strip of scarred wooden workbench with a black ink slab and loose metal type appears at the lower right. Warm daylight from the upper right grazes the paper, revealing the contrast between the matte printed lettering and the uninked recessed motifs. The palette is restrained ivory, black, deep indigo and a single blue accent, with authentic handmade letterpress character and elegant tone-on-tone paper craftsmanship.", "wh_ratio": "1:1"}

Metallic Numeral Six in Cyan Glow
A metallic ribbon forms a stylized numeral six, positioned centrally against a neutral background with a straight-on camera angle. Render this in the following style: deep blue and cyan palette, glowing code highlight, low saturation contrast, dark ambient lighting, subtle skin texture rendering, sharp focal depth, shallow field focus, digital illustration effect, futuristic data aesthetic, high-contrast edge definition, volumetric light treatment, hyper-realistic medium, cold chromatic tone, soft gradient blur, tech-noir finish Do not introduce any subject, object, or background from the style reference. Preserve the original composition, pose, and framing. No text, letters, words, signatures, or watermarks anywhere in the image. <lora:flux3_klein_sd_lora_rank_256_bf16:1>

Patagonia Ridge Hiker Poster
A majestic high-angle wide shot captures a lone hiker with a red backpack trekking along a narrow, rugged ridge path that winds into the distance. The hiker is seen from behind and slightly above, appearing as a dark silhouette against a dramatic backdrop of jagged, grey granite peaks that pierce through layers of low-hanging, ethereal white clouds. The terrain beneath their feet is a mix of steep, grassy green slopes and exposed, striated rock faces where the path hugs the very edge of a precipice. Dominating the upper sky above the mountains is a large, sweeping typography of the word "PATAGONIA" rendered in a bold, rust-orange serif font that partially obscures the clouded atmosphere, while smaller sans-serif text reading "CHILE" sits centered at the very top edge of the frame. The entire scene is bathed in soft, diffused light suggesting early morning or late afternoon, creating a profound sense of scale and vast, misty grandeur. The aesthetic is a seamless blend of realistic landscape photography and graphic design, possessing the crisp clarity of vintage travel posters with rich atmospheric contrast and deep earthy color tones.

Happy 3D Stars Flying Forward
Four happy 3D rounded stars flying into camera with different tilt and angle. Dark blue, almost black background with tiny stars. PlayStation 3 games style. Refined 3D perspective poster. [{"id": "obj_1", "bbox": [547, 54, 953, 625], "desc": "Yellow rounded 3D star with happy mouth and black oval eyes"}, {"id": "obj_2", "bbox": [62, 607, 266, 875], "desc": "Blue rounded 3D star with happy mouth and black oval eyes"}, {"id": "obj_3", "bbox": [219, 268, 484, 625], "desc": "Pink rounded 3D star with happy mouth and black oval eyes"}, {"id": "obj_4", "bbox": [375, 464, 734, 946], "desc": "Green rounded 3D star with happy mouth and black oval eyes"}]

Latte vs Cappuccino Poster
Charming, aesthetically pleasing photo info-graphic poster for a small cafe. In the center is a clear glass mug split vertically down the middle by a thin, dotted line. Left Side (LATTE): The glass is filled mostly with creamy, light-brown steamed milk, topped with a thin layer of microfoam and simple, elegant latte art. Right Side (CAPPUCCINO): The glass has distinct layers: a dark-espresso base, a generous layer of steamed milk, and a thick, airy head of frothy milk foam, topped with a sprinkle of cocoa powder. The entire poster has a soft and warm texture. Printed on hand made paper. Above the glass, the title "LATTE vs. CAPPUCCINO" is written in modern script. On either side of the split glass, three numbered points are listed. Left (Latte): More Steamed Milk, Milder & Smoother, Small Layer of Foam. Right (Cappuccino): Balanced Milk/Foam, Richer Espresso, Thicker Frothy Cap. The background is a soft cream color, decorated with subtle coffee beans and floral motifs. The poster has a rustic, cozy feel, framed by a delicate line border. At the very bottom, "Nerd Cafe" is subtly written.

Future Orbit Spacecraft Poster
Japanese manga-style poster built around a large oil painting on textured canvas, with bold black ink outlines, halftone accents, speed lines, and oversized display typography. Across the top, thick white Japanese lettering reads "宇宙探検" in a heavy condensed font with red shadowing; beneath it, smaller uppercase text reads "FUTURE ORBIT". The central painted scene fills most of the poster: a futuristic spacecraft hovers prominently in the foreground at a low three-quarter angle, looming above the viewer. Its sleek cylindrical body is predominantly vermilion red, edged with sharp silver metallic bands, dark gunmetal joints, riveted panels, heat-stained seams, antenna housings, sensor arrays, and multiple protruding structures including side-mounted engines, articulated fins, radar dishes, and narrow mechanical appendages. White exhaust flames burst from two rear thrusters, casting warm orange light across the hull and deep shadows between its components. Angular manga highlights trace the curved metal surfaces while visible oil brushstrokes give the red paint layered texture. Behind the vessel, a distant blue-violet planet curves through the upper background, wrapped by a bright cyan atmospheric rim. A small cratered moon orbits near the planet’s right side. Dense stars, violet nebulae, turquoise gas clouds, and sweeping magenta cosmic dust fill the surrounding space. Along the bottom, jagged cream-colored manga lettering reads "BEYOND THE STARS", framed by red starbursts and diagonal motion marks. Thick black borders, offset color blocks, and exposed woven canvas fibers surround the painted composition, blending precise metal textures, fabric-like shading, oil-paint depth, and graphic manga energy into one unified exploration poster.
How to write great FLUX 3 prompts
- 1Name the medium first. Many prompts here say what kind of picture it is before anything else: an ink drawing on rice paper, a humorous cartoon illustration, wildlife photography, or just the word photorealistic. That opening phrase sets the look that the rest of the description builds on.
- 2Describe the scene in sentences. Most prompts on this page read as a paragraph rather than a string of tags: who or what, where, what is happening, then light and colour. The comma-separated tag lists familiar from older Civitai models are a small minority here.
- 3Spell out the framing. The detailed prompts here say how the subject sits in the frame: the head filling the composition from edge to edge, viewed straight-on, one side cropped by the border; front-facing; a close-up; a wide angle. Write the framing you want instead of leaving it to the subject's usual pose.
- 4Quote any words that should appear. When a prompt here wants text in the image, it puts the exact words in quotes and says how they are written: in frosting, in sloppy handwriting, in large yellow letters. Look at the image on the card to see how that came out before you rely on it.
- 5Delete stray LoRA trigger words. A Civitai prompt can carry the trigger word of a LoRA the creator loaded, often an odd string next to a style name, and without that LoRA it does nothing. Posts that list a LoRA are left out of this page, but a trigger word can survive in a prompt whose post does not list one.
- 6The settings are not in the prompt. Civitai records the seed, sampler, step count, guidance and size next to each image, and they shape the result as much as the words do. Copy the prompt alone and expect a different picture of the same idea.
- 7Say what to take from a reference, and what not. Some X prompts here are written for a face photo you attach: they take the face and hair from image 1 and say outright not to use its outfit, pose or background. They need a tool that accepts a reference image, and you should only use photos you have the right to use.
Prompt formula
Medium or style first + subject + what is happening + setting + framing and viewpoint + light and colour + any exact text in quotes, and how it is written
Example from the collection, quoted as posted (TheP3NGU1N on Civitai): photorealistic. A penguin holds a birthday cake over the edge of a trashcan about to drop it into the trashcan, on the cake written in frosting using sloppy handwriting "FLUX 3, WE TRIED!" the penguin is in a living room at a birthday party for other penguins.
Frequently asked questions
What is FLUX 3, and what are Flux.3 Klein and Klein-base?
FLUX 3 is Black Forest Labs' image model line, and Flux.3, Flux.3 Klein and Flux.3 Klein-base are the three base-model labels Civitai files its images under. We have not tested the three side by side, so we do not describe how they differ; the creator's post and Black Forest Labs' own pages are the place to check. Every card links back to its post.
Can I run these prompts on apimodels.app?
No: apimodels.app does not offer a FLUX 3 image model, so these prompts cannot be run as images through our API. What we do run is FLUX 3 Max (flux-3-max), a video model that is a variant of FLUX 3 Video: it turns a prompt, a first frame with an optional last frame, or up to 10 timed keyframes into a 5 to 20 second clip with sound, at $0.221 per second at 720p and $0.377 at 1080p. To run an image prompt from this page, use a tool that offers the FLUX 3 version it was written for; each card links the original post.
What is the difference between a FLUX 3 image prompt and a FLUX 3 video prompt?
An image prompt describes one still moment, while a video prompt also has to say what moves, how the camera moves, how long it lasts and what it sounds like. Pasted into FLUX 3 Max, a prompt from this page will give you a clip, but the motion and the sound are left to the model. The better route is to use the finished still as the first frame and write the movement in the prompt. FLUX 3 video prompts have their own page on this site.
Why does my image not match the one on the card?
Because the prompt is only part of what made the picture. A Civitai image also depends on the base model (Flux.3, Klein or Klein-base), the seed, the sampler, the step count, the guidance and the size, and sometimes on a trigger word for a LoRA the creator loaded. Copy those settings from the original post where it shows them, and expect a different take on the same idea where it does not.
Who wrote these prompts?
The people who posted the images did, on Civitai and X, and we did not write or edit any of them. Each card quotes the prompt in full, word for word, names the author and links the original post. The prompts and images belong to their creators; our own notes and data are licensed CC BY 4.0. To correct a credit or have an entry removed, email us or open an issue on the GitHub repository.
Did apimodels.app generate the images on this page?
No: every image is the one the creator posted with the prompt, shown from the original post. We did not generate, edit or re-upload any of them.
Can I use these prompts and images commercially?
The prompts and images belong to their creators, so check the original post before reusing a prompt commercially. For images you make yourself, check the license of the FLUX 3 model you run and the terms of the tool you run it in.
FLUX 3 images are not generated on apimodels.app
We do not run a FLUX 3 image model, so these prompts cannot be turned into images through our API. We do run FLUX 3 Max, the video model: send one of these images as the first frame, or pin several as timed keyframes, and get a 5 to 20 second clip with sound, from $0.221 per second. Failed tasks are not charged.