Appy Pie Launches PixelForge, Vibeo AI Models for Image and Video Generation

Appy Pie's new PixelForge AI model is a text-to-image generation model.

Written by Akash Dutta, Edited by David Delima | Updated: 16 April 2025 19:38 IST

Highlights

Vibeo accepts both text and images as input
Both the AI models can be accessed via the Appy Pie Design platform
The Appy Pie Design platform costs Rs. 80 a month

Appy Pie Launches PixelForge, Vibeo AI Models for Image and Video Generation

Appy Pie is pitching the new AI models to individuals, startups, and enterprises

Photo Credit: Pexels/Antoni Shkraba Studio

Appy Pie, an Indian artificial intelligence (AI) no-code platform, launched two new AI models on Tuesday. Dubbed PixelForge and Vibeo, these are multimodal large language models that can generate images. and videos. The former is a text-to-image model, whereas the latter can generate videos from a text or image input. The company is pitching the new products to both individuals as well as businesses via its Appy Pie Design platform. Notably, the company also offers AI tools to users to let them develop mobile apps, websites, and AI chatbots.

Appy Pie Launches Two New AI Models

The company says PixelForge and Vibeo are proprietary models that were built and trained in-house from scratch. The new large language models (LLMs) arrive as the successor to the Flawless Text AI model, which was focused on text generation. The company said the new models would be useful for creators, marketing professionals, and businesses.

PixelForge is a text-to-image generation model. The company claims it can generate high-resolution, photorealistic, and artistic visuals from text prompts. It is said to be optimised for versatility and supports a wide range of styles, compositions, and use cases.

After ChatGPT and Gemini, Anthropic's Claude Might Get a Voice Mode

While Appy Pie says that the model's capabilities are similar to OpenAI's DALL-E and Stability AI's Stable Diffusion models, it did not share any benchmark scores that confirm these claims.

The company also did not share information about the output image's resolution, rate limits, or credits offered. The AI model's architecture, training processes, and source of procured data are also currently known.

Coming to Vibeo, it is a video generation model that supports both text and images as input. This means users can generate a video with a natural language text prompt or by sharing a reference image. The company claims that the AI model is focused on realism and can contextually understand the prompt to capture the mood and motion of the desired video.

Gemini Advanced Users Can Now Generate Videos Using Veo 2 AI Model

However, technical details such as video duration, resolution, and any daily or monthly rate limits are currently unknown.

OpenAI Could Soon Enter the Social Media Space to Take on Meta and X

To access these AI models, users and businesses must visit the Appy Pie Design platform. Accessing the website requires a monthly subscription of Rs. 80, which is charged on an annual basis. Gadgets 360 staff members were not able to access the website, and could not confirm if the platform charges any add-ons for the services.

For the latest tech news and reviews, follow Gadgets 360 on X, Facebook, WhatsApp, Threads and Google News. For the latest videos on gadgets and tech, subscribe to our YouTube channel. If you want to know everything about top influencers, follow our in-house Who'sThat360 on Instagram and YouTube.