APIMODELSAPIMODELS

FLUX 3 Product & Food 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.

← All 401 FLUX 3 prompts

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)

Buzz Cola Bottle Label

Buzz Cola Bottle Label

A bottle with label that depicts a cartoonish woman saying gimme some Buzz Cola in large Yellow Letters with a cartoonish Lightening bolt. The bottle is brown , the label is blue. The bottle has condensation droplets, bight club background.

by That70sGuySource
Black Forest Lager Beer Can

Black Forest Lager Beer Can

A craft beer can on a mossy stone with a hand-lettered label reading "BLACK FOREST LAGER", "Brewed with three hops" and "4.8% ABV" in small print, condensation droplets, forest bokeh background

by CivitaiOfficialSource
Red Craft Beer Can on Stone

Red Craft Beer Can on Stone

REDQW21 Ale beer 5%, the beer can is red: A craft beer can on a mossy stone with a hand-lettered label reading "RedCraft QW21Fixed", "Brewed with Turbo hops" and "5% ABV" in small print, condensation droplets, forest bokeh background

by AiMeASOPSource
Whiskey Glass and Bourbon Bottle

Whiskey Glass and Bourbon Bottle

Bradhamel art style. A rustic, weathered interior scene featuring a cracked blue-painted wooden table with a glass of amber whiskey and ice cubes beside an aged, unlabeled glass bottle of bourbon, set against a backdrop of peeling blue paint walls and a faded blue shuttered window; warm golden light from a wall-mounted lamp casts dramatic shadows and highlights the textures of decay and patina, evoking a moody, nostalgic atmosphere with rich earthy tones and deep contrasts, captured in a photorealistic still life composition with shallow depth of field emphasizing the drink and bottle as focal points.

by nikonac1808Source
Muffin and Latte Cafe Table

Muffin and Latte Cafe Table

masterwork, masterpiece, best quality, very aesthetic, absurdres, newest, huge filesize, hires, highres, supper fine illustration, very awa, detailed, hdr, blurry background, no humans, food, food focus, muffin and Caffè Latte, cafe, table, smooth, shallow depth of field, natural light, warm tones, cozy background, artisan, pastel tones, ambient reflection,

by moyoriSource
Motorcycle in Cyberpunk Studio Render

Motorcycle in Cyberpunk Studio Render

A motorcycle is positioned centrally in the frame with a three-quarter view showing both wheels and handlebars against a plain background. Render this in the following style: digital 3d rendering, vibrant blue orange and teal palette, soft diffused lighting, smooth digital finish, shallow depth of field focus, sci-fi cyberpunk aesthetic 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>

by gonzaluSource
Interlocking Metallic S Blocks

Interlocking Metallic S Blocks

Two metallic S-shaped blocks interlock at the center of a neutral background with even lighting and eye-level perspective. Render this in the following style: 3d render, desaturated blue-gray hue, flat even lighting, diffuse shadow, smooth digital finish, straight perspective rendering, neutral tone, technical illustration aesthetic, precise edge, soft texture, clean gradient, schematic treatment, top-down focus, muted contrast, minimal grain, blueprint film, industrial palette 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>

by gonzaluSource
Coffee Splash Fractal

Coffee Splash Fractal

Photorealistic high-speed photograph of swirling geometric fractal splashes of coffee liquid flying through the air above a cup on a table, captured with a long exposure-like frozen instant that preserves every droplet as a sharply defined form. A narrow beam of morning sunlight enters from the upper left, cutting diagonally across the scene and illuminating the airborne spray while the right side falls into cool shadow. In the lower center, a white ceramic cup filled with dark brown coffee rests off-center on a worn walnut tabletop, its curved handle pointing toward frame-right. The rising splash erupts from the rim in an enormous spiral: concentric tendrils curl outward like recursive fern fronds, branching into repeating arcs, spirals, lattices, and self-similar loops. Hundreds of suspended coffee droplets transform into intricate fractal structures, with broad translucent sheets folding around dense black-brown cores and thin amber edges where the sunlight passes through them. Near the cup, small beads break into star-shaped bursts; higher in the composition, they expand into sweeping whorls resembling mathematical mandalas, each branch dividing into smaller matching curls. Several large fluid ribbons cross one another at different angles, creating a dynamic diagonal sweep from the cup toward the top corners. Tiny droplets scatter beyond the main formation, including isolated pinpoints near the left edge and elongated teardrop shapes along the far right. On the table below, a shallow puddle reflects fragments of the spiral, beside two stray coffee drops and a faint circular stain. The background is a plain pale wall crossed by the bright rectangular shaft of sunlight, leaving the outer regions uncluttered so the illuminated fractal coffee remains dominant.

by gonzaluSource
Burrito Ad with Toes Sticking Out

Burrito Ad with Toes Sticking Out

Advertising photo. Delicious Burrito with foot in the roll. The toes sticking out of the burrito. The caption: "Burritoes."

by NeuronomiconSource
Key Necklace in Woman's Hand

Key Necklace in Woman's Hand

close up on small key necklace in woman hand. nails are polished and pretty.

by liutyiSource
Dust-Sculpted Ceramic Teapot

Dust-Sculpted Ceramic Teapot

A ceramic teapot sits in the upper left, sculpted from solidified dust suspended mid fall inside a vacuum chamber. Render it as intaglio engraving method, etching the suspended dust into deep, linear grooves.

by gonzaluSource
French Fries in Red Envelope

French Fries in Red Envelope

Advertising photo. A red cardboard envelope with French fries. The French fries look like toes sticking out of the envelope. Toes made of potato. The caption: "Potatoes."

by NeuronomiconSource
Cube Pie with Alien Fruit

Cube Pie with Alien Fruit

a pie shaped like a cube it is overflowing with bizarre alien fruits. the fruit filling is so moist and juicy. setting is a cyberpunk restaurant at sunset with alien suns.

Gold Drop Earring Close-Up

Gold Drop Earring Close-Up

A close-up photograph focuses on a nice young woman left ear, featuring a multi-layered gold drop earring. The earring has two chains of different lengths with three cubic zirconia-studded flower clusters connected by thin chains and small gold beads. The person has blonde hair, light skin, and is looking slightly downwards with their head tilted to the right. A hand with neatly manicured nails rests near the hair. The setting is an indoor studio with a soft, warm light and a neutral, textured background.

by liutyiSource

How to write great FLUX 3 prompts

  1. 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.
  2. 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.
  3. 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.
  4. 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.
  5. 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.
  6. 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.
  7. 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.

Other prompt libraries