Plutonic Rainbows

I’ve upgraded my application by integrating a transformer-based model for intent classification, which moves beyond the basic, rule-based system I used initially. Now, instead of relying on simple keyword checks, my app calls a smaller, efficient DistilBERT model that can pick up on more nuanced language patterns. This change makes my pipeline more sophisticated and better prepared for future improvements, such as fine-tuning on my own dataset to achieve domain-specific accuracy.

In addition, I’ve tackled the stability and resource issues I faced before by using a smaller model and explicitly setting it to run on the CPU. This reduces the risk of crashes or silent failures. I’ve also maintained my spaCy-based entity extraction and GPT‑4 integration for generating insights, so my app still returns refined prompts and thorough AI responses. Overall, I feel that my setup is now more robust, extensible, and aligned with best practices in modern NLP.

Now available for Pro users, with Plus users gaining access next week. I tested it through the API — it’s impressive but significantly more expensive than other models. Hopefully, the cost will decrease soon.

• I have added wan-i2v templates for file upload and video generation.

• Open AI have added ten requests a month to Deep Research for Plus Users.

• Started building Prompt Refiner application.

• Built application launcher for Flux.1 [Dev] templates.

I discovered that my app was failing to display the generated video because I was incorrectly extracting the video URL from the Fal.ai API response. Initially, my code assumed the video data was inside a property called data (i.e., final_obj.data), but in reality, the final result was returned directly as a plain dictionary in final_obj with the structure {"video": {"url": "..."}}. Once I logged the final API response, I realised I needed to use final_obj directly to extract the video URL. This change fixed the issue, and now the correct URL is passed to the template, allowing the video to display as intended.