3D : un objet 3D à partir d'une photo produit
Transformer une photo produit en objet 3D avec TripoSR : préparer l'image, lancer la reconstruction et exporter un fichier 3D.
Template
Photo d'un seul objet, centré, sur fond uni, entièrement visible, sans reflet fort ni ombre dure.
Settings
| Entrée | une image (PNG ou JPG) |
|---|---|
| Sortie | maillage 3D (OBJ ou GLB) |
| Commande | python run.py photo.png --output-dir sortie/ |
Notes
TripoSR reconstruit l'objet à partir d'une seule image : plus le fond est simple, plus le résultat est propre. Modèle sous licence MIT.
Estimated cost
Input tokens per call : ≈ 231
| Model | Per call | Per 1,000 calls |
|---|---|---|
| Mistral Large · Mistral AI | €0.00010 | €0.10 |
| DeepSeek Flash · DeepSeek | €0.00006 | €0.06 |
| DeepSeek V4 Pro · DeepSeek | €0.00027 | €0.27 |
| GPT-6 Luna · OpenAI | €0.00002 | €0.02 |
| GPT-6 Sol · OpenAI | €0.00041 | €0.41 |
| Claude Sonnet 5.5 · Anthropic | €0.00041 | €0.41 |
| Claude Opus 5.5 · Anthropic | €0.00081 | €0.81 |
| Self-hosted open-source model (Ollama, vLLM) | €0 in API fees (server cost only) | |
Input cost only, excluding the model's answer. Providers' public standard prices (Mistral AI, DeepSeek, OpenAI, Anthropic) converted from USD to euros at the ECB rate of September 29, 2026. Estimate: 1 token ≈ 3.6 characters.
Common to all 3 regions
Created by the author, no outside source.
Commercial use allowed · credit the author · changes allowed.
Text or data only: no access to files, network or commands.
Hosted in France (Scaleway, Paris). No transfer outside the EU.
European Union · 5/5
No personal data.
No training data: no summary required.
United States · 5/5
No personal data.
No training data: no documentation to publish.
China · 5/5
No personal data.
No training data; AI-generated content published in China must be labelled (2025).
Indicative summary as of 30/09/2026, not a legal certification. Method and sources →
Pin a version in your code
import contexte p = contexte.load("contextetech/objet-3d-photo-produit-triposr", version=1) print(p.fill())
$ contexte get k7vyc0#v1 Statistics
Likes : 0 · Comments : 0
Click a counter to show or hide it, hover the chart for details. One view per visitor per day, bots excluded; counting started on 30 September 2026.
- Identifier
- contextetech--objet-3d-photo-produit-triposr
- Type
- Prompts
- File
- objet-3d-photo-produit-triposr.json
- Format
- JSON (application/json)
- Size
- 692 bytes
- Encoding
- UTF-8
- Estimated tokens
- ≈ 191
- Language
- French
- License
- MIT
- Commercial use
- Allowed
- Personal data
- None
- Version
- 1.0
- Published on
- October 2, 2026 at 1:49 PM
- Updated on
- October 2, 2026 at 1:49 PM
- Storage
- in database
- Uses
- 0
- Likes
- 0
Python contexte
$ pip install contexte import contexte p = contexte.load("contextetech/objet-3d-photo-produit-triposr") print(p.fill())
$ contexte get k7vyc0 objet-3d-photo-produit-triposr.json
{
"format": "contextec/prompt/v1",
"id": "contextetech/objet-3d-photo-produit-triposr",
"description": "Transformer une photo produit en objet 3D avec TripoSR : préparer l'image, lancer la reconstruction et exporter un fichier 3D.",
"tags": [
"triposr",
"image-vers-3d",
"e-commerce"
],
"license": "MIT",
"language": "fr",
"modality": "3d",
"template": "Photo d'un seul objet, centré, sur fond uni, entièrement visible, sans reflet fort ni ombre dure.",
"variables": [],
"tool": "TripoSR",
"params": {
"Entrée": "une image (PNG ou JPG)",
"Sortie": "maillage 3D (OBJ ou GLB)",
"Commande": "python run.py photo.png --output-dir sortie/"
}
}
Community
No comments yet. Share your feedback, it will help the next person.