bmoefvec/flux-kontext-prompts-fr
bmoefvec/flux-kontext-prompts-fr has 70 GitHub stars and 0 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-18 12:18 UTC. Last push 2026-10-16.
Measured star growth
- in 24h
- 0
- in 7 days
- Collecting history
- in 15 days
- Collecting history
- in 1 month
- Collecting history
Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.
About
FLUX Kontext prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`flux-kontext-pro`) and the cost per image.
Creative & MediaREADME.md
OriginalFLUX Kontext Prompts — 8 Tested Recipes With Outputs
from $0.032 per image — un seul endpoint compatible OpenAI sur
https://api.apimart.ai/v1, sans abonnement mensuel. (relevé le 2026-10-12)
Get an API key · Live pricing · Model page · ⚡ 60-second quickstart
Pourquoi les équipes passent par APIMart pour FLUX Kontext (flux-kontext-pro)
- Une clé, tout le catalogue. La même base URL
https://api.apimart.ai/v1et le même en-têteAuthorizationdonnent accès à FLUX Kontext (flux-kontext-pro) et à plus de 300 autres modèles d'image, de vidéo et de langage — changez le champmodel, pas votre client. - $1 minimum, paiement à l'usage. Ni abonnement ni forfait prépayé à dimensionner à l'avance : rechargez à partir de $1 et consommez-le en appels.
- Le montant revient dans la réponse. Chaque tâche terminée indique le montant facturé (
cost/credits_cost) ; une tâche marquéefailedest remboursée. - Asynchrone par conception. Soumettez, récupérez le
task_id, interrogezGET /v1/tasks/{id}— le traitement par lots et les retries relèvent d'une file d'attente ordinaire, pas d'une intégration sur mesure.
Eight FLUX Kontext prompts listed with an example render, the ratio, and what the call costs on this route. Copy a recipe, keep the structure, swap the subject.
- Model:
flux-kontext-pro - Recipes: 8 (machine-readable in
data/prompts.json, table inPROMPTS.md) - Effective price used below: $0.032 per image — estimated cost of the whole set: $0.256
What separates a usable recipe from a wasted call
Three rules held up across every render in this set:
- Name the material, not the adjective. "Frosted glass", "matte ceramic", "layered paper" steer rendering far more than "beautiful" or "high quality".
- Set the light explicitly. "Single softbox from the left", "golden hour backlight", "focus-stacked studio light" remove the guesswork the model would otherwise do for you.
- Pin the framing. Ratio plus lens language (
85mm,24mm,macro, overhead flat lay) decides whether the output drops into a layout unchanged.
Prompt structure cheat-sheet
| Slot | What to write | Example |
|---|---|---|
| Subject | one concrete object or person, with material | frosted glass perfume bottle |
| Light | direction + quality | single softbox from the left |
| Framing | ratio + lens or distance | 3:4, medium format look |
| Setting | surface, backdrop, environment | wet black stone slab |
| Finish | render or film character | commercial product photography |
The gallery
Each row is one recipe: example render, category, ratio, cost on this route and the exact prompt.
| Output | Recipe | Ratio | Cost | Prompt |
|---|---|---|---|---|
![]() |
Product / e-commerce | 1:1 | $0.032 | Studio hero shot of a frosted glass perfume bottle on a wet black stone slab, single softbox from the left, faint mist, deep charcoal background, crisp label text, commercial product photography |
![]() |
Food photography | 4:3 | $0.032 | Overhead flat lay of a spicy miso ramen bowl with soft boiled egg, nori and scallions, dark ceramic table, chopsticks resting on the rim, natural window light, editorial food photography |
![]() |
Cinematic still | 16:9 | $0.032 | Rain soaked Kyoto alley at night, paper lantern reflections on wet stone, a lone figure with a transparent umbrella walking away, cinematic 35mm still, shallow depth of field, film grain |
![]() |
Architecture | 16:9 | $0.032 | Minimalist concrete villa on a cliff at dusk, warm interior light, infinity pool reflecting a violet sky, architectural photography, 24mm perspective, ultra sharp |
![]() |
Fashion portrait | 3:4 | $0.032 | Editorial fashion portrait of a model in an oversized ivory wool coat, seamless light grey studio backdrop, crisp high key lighting, medium format detail, calm expression |
![]() |
Illustration | 1:1 | $0.032 | Layered paper cut illustration of a mountain lake at sunrise, five depth layers, soft pastel palette, subtle drop shadows, art print composition, clean vector edges |
![]() |
Design / UI | 16:9 | $0.032 | Flat vector dashboard panel showing three gauge dials and abstract latency curves, muted blue and sand palette, generous white space, crisp geometric cards, no placeholder text |
![]() |
Macro nature | 3:2 | $0.032 | Macro photograph of a dew covered dandelion seed head against deep black background, focus stacked detail, iridescent droplets, studio lighting |
Run a recipe yourself
export APIMART_API_KEY=...
python examples/run_recipes.py --dry-run # list the recipes, no network
python examples/run_recipes.py --limit 2 # generate two of them
curl --request POST --url https://api.apimart.ai/v1/images/generations \
--header "Authorization: Bearer $APIMART_API_KEY" --header 'Content-Type: application/json' \
-d '{"model":"flux-kontext-pro","prompt":"<paste a prompt>","size":"1:1","resolution":"1K"}'
Result links expire 72 hours after completion, so store the outputs; the completed task carries cost for reconciliation.
FAQ
Are these prompts free to reuse?
Yes — the prompt text in this repository is MIT licensed. The generated images and any third-party marks they contain remain your responsibility, and you should check the model vendor's terms before publishing commercial work.
Why do the recipes use different aspect ratios?
Because ratio is a layout decision, not a style one: 1:1 for catalogue and icons, 16:9 for hero and video thumbnails, 3:4 or 2:3 for portraits and print. Pinning it up front avoids cropping later.
How much does one recipe cost to run?
from $0.032 per image. Every completed task reports the exact amount in its cost field; a failed task is refunded.
Can I use a recipe as a template for another subject?
That is the point. Keep the structure (subject + light + framing + setting + finish) and replace the subject; changing everything at once makes it impossible to tell which phrase moved the output.
Related repositories
- Same model, this language — the other half of this pair: flux-kontext-api-fr
- Same model, other languages — 9 more language builds: 中文
flux-kontext-api-cn· Deutsch flux-kontext-api-de · Español flux-kontext-api-es · Relay/gatewayflux-kontext-api-gateway· Bahasa flux-kontext-api-id · 日本語 flux-kontext-api-ja · 한국어 flux-kontext-api-ko · Português flux-kontext-api-pt · Русский flux-kontext-api-ru - More models in this language — midjourney-api-fr · gemini-2-5-flash-image-preview-api-fr · nano-banana-api-fr · gemini-3-1-flash-image-preview-api-fr · nano-banana-2-api-fr · gemini-3-pro-image-preview-api-fr
- Topic hubs — every build of this model, all languages: flux-kontext · flux-kontext-api
This repository is one build in a cross-linked set of API guides for the same model family; each language build links back to the others.
Attributed links (how this repository is measured)
| Purpose | Attributed link | Target |
|---|---|---|
| Model page | https://go.apimart.ai/k-25157b | apimart.ai/fr/model/flux-kontext |
| Live pricing | https://go.apimart.ai/k-af0441 | apimart.ai/fr/pricing |
| Get an API key | https://go.apimart.ai/k-fbcb7c | apimart.ai/fr/keys |
Outbound APIMart links are minted through the promo link API; hand-made tracking parameters are rejected by
tools/check_links.py in CI.
Disclosure
FLUX Kontext is a third-party model served through APIMart. This repository publishes prompts, example renders and cost logic; it does not claim official status for any vendor, and model names and documentation belong to their owners.
Repository map
README.md gallery, prompt structure and FAQ
PROMPTS.md every recipe in one table
data/prompts.json machine-readable recipes with per-unit cost
examples/run_recipes.py batch runner (dry-run safe for CI)
tools/check_links.py attribution guard
assets/ example renders via the APIMart image API (JPEG)
License
MIT — see LICENSE.






