Octagram Creative

We ran two very quick tests on Weavy using the Nike Mercurial 10 Elite boot images.
Test 1: 2D to 3D:
- input: four images from different angles
- model used: Rodin 3D (the only one that allows for the above input)
- result: the 3D model is not usable for e-commerce purposes*

Test 2: Placing product in a contextual environment:
- input: one image and structured prompt
- models used: Gemini 2.5 Flash, Gemini 3 and Seedream v 4.5
- results: promising and can definitely be improved with additional prompt variations and refinements and parameters tweaking.

*𝘈𝘭𝘵𝘦𝘳𝘯𝘢𝘵𝘪𝘷𝘦 𝘢𝘱𝘱𝘳𝘰𝘢𝘤𝘩𝘦𝘴 𝘧𝘰𝘳 2D 𝘵𝘰 3D:
- 𝘨𝘦𝘯𝘦𝘳𝘢𝘵𝘪𝘯𝘨 𝘢 3𝘋 𝘱𝘳𝘰𝘥𝘶𝘤𝘵 𝘷𝘪𝘥𝘦𝘰 𝘧𝘳𝘰𝘮 2𝘋 𝘪𝘮𝘢𝘨𝘦𝘴 𝘸𝘩𝘪𝘤𝘩 𝘢𝘭𝘭𝘰𝘸𝘴 𝘧𝘰𝘳 𝘦𝘹𝘤𝘦𝘭𝘭𝘦𝘯𝘵 𝘱𝘳𝘰𝘥𝘶𝘤𝘵 𝘤𝘰𝘯𝘴𝘪𝘴𝘵𝘦𝘯𝘤𝘺, 𝘵𝘦𝘹𝘵𝘶𝘳𝘦 𝘢𝘯𝘥 𝘥𝘦𝘵𝘢𝘪𝘭𝘴 𝘱𝘳𝘦𝘴𝘦𝘳𝘷𝘢𝘵𝘪𝘰𝘯 (𝘢𝘴 𝘴𝘩𝘰𝘸𝘯 𝘩𝘦𝘳𝘦: https://www.facebook.com/share/v/1AGXpDumXF/)
- 𝘳𝘶𝘯𝘯𝘪𝘯𝘨 3𝘋 𝘱𝘳𝘰𝘥𝘶𝘤𝘵 𝘴𝘤𝘢𝘯 𝘢𝘯𝘥 𝘧𝘶𝘳𝘵𝘩𝘦𝘳 𝘳𝘦𝘧𝘪𝘯𝘪𝘯𝘨 𝘰𝘧 𝘵𝘩𝘦 3𝘋 𝘮𝘰𝘥𝘦𝘭

We are constantly exploring Generative AI use-cases grounded in real business needs. Product consistency, repeatable results and their applicability are key considerations in all our explorations as our aim is to transform experiments into scalable client-ready services.

We can now reliably produce 3D shoe visualisations using Generative AI alone from still images without any traditional 3D modelling (we never had this capability in house).
Our workflow can consistently generate 180° visualisations and we are confident that full 360° rotations will be possible soon.

For this particular test case we decided to use photos of a 𝐰𝐨𝐫𝐧 "Nike Manoa" boot (which belongs to one of our colleagues 😄) photographed by us in imperfect lighting conditions.
This way we can demonstrate how accurately the worn signs are reproduced and show the quality of the 3D visualisation derived from lower quality images.

IMAGE TO VIDEO PROOF-OF-CONCEPT AD FOR KAY SAKE
We continue running practical experiments with generative A.I. and looking for ways to achieve a good mix of conventional content production and generative A.I.
Most recently we made an experimental ad for our client KAY Sake.
This is a proof-of-concept, not an official ad. It is obvious the result isn’t yet polished to the client’s standards, but we wanted to test current capabilities of generative A.I. tools (in this case Google Veo), especially for keeping product visuals consistent across short video assets.
The piece was generated from a photo of the real KAY Sake bottle. Among key challenges we tried refining and which they’re still not perfect we can mention:
- Though the bottle and label layout are exactly the same as the real product, the small copy is not rendered correctly
- Turning a horizontally laid bottle fully upright, right now is only ~45°.
- Unscrewing the metal cap: getting the motion and mechanics to look authentic
- Frame consistency in the right side viewport
- Returning the bottle to the exact start pose at the end of the clip.

With additional time and further iteration, we are confident this ad can reach production quality. We also anticipate having more control over specific details in the near future.

𝘗𝘭𝘦𝘢𝘴𝘦 𝘯𝘰𝘵𝘦 𝘵𝘩𝘢𝘵 𝘵𝘩𝘪𝘴 𝘷𝘪𝘥𝘦𝘰 𝘪𝘴 𝘢𝘯 𝘦𝘹𝘱𝘦𝘳𝘪𝘮𝘦𝘯𝘵 𝘢𝘯𝘥 𝘯𝘰𝘵 𝘢𝘯 𝘰𝘧𝘧𝘪𝘤𝘪𝘢𝘭 𝘢𝘥. 𝘍𝘰𝘳 𝘰𝘧𝘧𝘪𝘤𝘪𝘢𝘭 𝘤𝘰𝘯𝘵𝘦𝘯𝘵 𝘢𝘯𝘥 𝘯𝘦𝘸𝘴 𝘧𝘳𝘰𝘮 𝘒𝘈𝘠 𝘱𝘭𝘦𝘢𝘴𝘦 𝘷𝘪𝘴𝘪𝘵 𝘵𝘩𝘦𝘪𝘳 𝘍𝘢𝘤𝘦𝘣𝘰𝘰𝘬 𝘱𝘢𝘨𝘦 KAY Sake 𝘢𝘯𝘥 𝘸𝘦𝘣𝘴𝘪𝘵𝘦 https://kaysake.com/ (𝘱𝘳𝘰𝘶𝘥𝘭𝘺 𝘥𝘦𝘴𝘪𝘨𝘯𝘦𝘥 𝘢𝘯𝘥 𝘥𝘦𝘷𝘦𝘭𝘰𝘱𝘦𝘥 𝘣𝘺 𝘖𝘤𝘵𝘢𝘨𝘳𝘢𝘮).

𝗕𝗥𝗘𝗪𝗜𝗡𝗚 𝗨𝗣 𝗦𝗢𝗠𝗘𝗧𝗛𝗜𝗡𝗚 𝗦𝗣𝗘𝗖𝗜𝗔𝗟
We are currently working with sake brand KAY to create a contemporary web presence for the fresh & up and coming brand.
The current landing page is replacing a usual "under construction" page, already building brand awareness and capturing early interest with a subscriber list while the full website is being developed.
The landing page UI is based on the brand identity and key visuals created by renowned Dutch designer Marcel Wanders.
The full website is on its way, stay tuned.

Short film "air head" created by "shy kids" using (by OpenAi).

We already know that Ai will have a huge impact on our industry, yet we are still surprised by the rapid evolution of generative Ai.
Sora is an AI model, at moment only available to a small group of digital creators, that can create realistic and imaginative scenes from text instructions.

Short film "air head" created by "shy kids" using (by OpenAi).
We already know that Ai will have a huge impact on our industry, yet we are still surprised by the rapid evolution of generative Ai.
Sora is an AI model, at moment only available to a small group of digital creators that can create realistic and imaginative scenes from text instructions.

Credits: shy-kids.com

Merry Christmas, everyone! 🎄

P.S. We’re preparing for the AI era. This Christmas tree was created using an AI program (Midjourney).