Merge pull request #2720 from oracle-devrel/removing-duplicate

Added new image generation asset

Author: aliottoman

ai/generative-ai-service/product-image-generation/LICENSE

@@ -0,0 +1,35 @@
+Copyright (c) 2025 Oracle and/or its affiliates.
+
+The Universal Permissive License (UPL), Version 1.0
+
+Subject to the condition set forth below, permission is hereby granted to any
+person obtaining a copy of this software, associated documentation and/or data
+(collectively the "Software"), free of charge and under any and all copyright
+rights in the Software, and any and all patent rights owned or freely
+licensable by each licensor hereunder covering either (i) the unmodified
+Software as contributed to or provided by such licensor, or (ii) the Larger
+Works (as defined below), to deal in both
+
+(a) the Software, and
+(b) any piece of software and/or hardware listed in the lrgrwrks.txt file if
+one is included with the Software (each a "Larger Work" to which the Software
+is contributed by such licensors),
+
+without restriction, including without limitation the rights to copy, create
+derivative works of, display, perform, and distribute the Software and make,
+use, sell, offer for sale, import, export, have made, and have sold the
+Software and the Larger Work(s), and to sublicense the foregoing rights on
+either these or other terms.
+
+This license is subject to the following condition:
+The above copyright notice and either this complete permission notice or at
+a minimum a reference to the UPL must be included in all copies or
+substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

ai/generative-ai-service/product-image-generation/README.md

@@ -0,0 +1,84 @@
+# SKU Image Studio — OCI GenAI
+
+*A Streamlit-based application that generates lifestyle and product imagery for retail SKUs using Oracle Generative AI. The asset automates the creation of market-localised, shot-type-specific product visuals from structured product inputs, eliminating manual photography briefing and reducing time-to-asset for high-volume SKU catalogues.*
+
+Author: Ali Ottoman
+
+Reviewed date: 27.03.2026
+---
+
+![Demo](sku_image_generation_studio.gif)
+
+---
+
+# When to use this asset?
+
+*This asset is used by retail, e-commerce, and digital transformation teams when high-volume, market-localised product imagery is required without manual photography overhead.*
+
+### Who
+- E-commerce teams managing large SKU catalogues requiring frequent visual refresh
+- Retail marketing teams producing localised imagery across multiple target markets
+- Digital transformation teams modernising manual product photography workflows
+
+### When
+- SKU volume makes per-product photography cost-prohibitive
+- Market-specific visual variants are required (regional demographics, settings, tone)
+- Rapid concept visualisation is needed before committing to a full production shoot
+- Consistent, brand-aligned output is required at scale
+
+# How to use this asset?
+
+*The asset is deployed as a Streamlit application and guides users through entering product details, selecting visual parameters, and generating imagery.*
+
+### Application Workflow
+1. Enter product details:
+   - Product name
+   - Description (positioning, materials, key attributes)
+2. Select visual parameters:
+   - Target market
+   - Shot type
+   - Setting / context
+3. Click **Generate Image**
+4. Review:
+   - Generated product image
+   - Metadata summary (market, shot type, setting, resolution)
+   - Prompt sent to the model (for auditability and iteration)
+   - Downloadable PNG output
+
+### Key Capabilities
+- Structured prompt construction from discrete UI inputs — no prompt engineering required from the operator
+- Market localisation across five regional profiles (Middle East, Western Europe, North America, South & Southeast Asia, Global)
+- Shot type control: Editorial, Candid, Flat Lay, On-Model, Product Only
+- Setting control: Studio, Home, Urban, Café, Nature
+- Full prompt transparency — the model prompt is surfaced in the UI for review and iteration
+- One-click PNG download per generated asset
+
+### File Structure
+```
+.
+├── app.py
+├── prompt_builder.py
+├── oci_client.py
+├── requirements.txt
+└── README.md
+```
+
+### Setup
+```bash
+pip install -r requirements.txt
+streamlit run app.py
+```
+
+Update `oci_client.py` with your `COMPARTMENT_ID` and `PROFILE_NAME`. 
+
+# Useful Links
+
+- OCI Generative AI Documentation
+  - https://docs.oracle.com/en-us/iaas/Content/generative-ai/home.htm
+
+# License
+
+Copyright (c) 2026 Oracle and/or its affiliates.
+Licensed under the Universal Permissive License (UPL), Version 1.0.
+
+See [LICENSE](https://github.com/oracle-devrel/technology-engineering/blob/main/LICENSE.txt) for more details.