PUMPG - MidJourney Prompt Generator vs Drag Your GAN

PUMPG is a free Midjourney prompt builder that turns dropdown selections and text fields into copy-ready prompts with the right parameters attached. You describe your main idea, pick model version, aspect ratio, stylize, chaos, and style filters, then copy the assembled string into Discord or the Midjourney web app.

Writing Midjourney prompts from memory means constantly looking up which versions accept --sref or what chaos values do. PUMPG lays out every parameter with tooltips and adds browsable style filters across architecture, art, characters, nature, and photography categories, so you build prompts visually instead of memorizing syntax.

PUMPG fits Midjourney users who want faster iteration without re-reading the docs for every flag. Advanced settings cover style references, character references, seed, speed, quality, stop, repeat, tile, and video output. A free login is required to continue using the tool.

In the realm of synthesizing visual content to meet users' needs, achieving precise control over pose, shape, expression, and layout of generated objects is essential. Traditional approaches to controlling generative adversarial networks (GANs) have relied on manual annotations during training or prior 3D models, often lacking the flexibility, precision, and versatility required for diverse applications.

In our research, we explore an innovative and relatively uncharted method for GAN control – the ability to "drag" specific image points to precisely reach user-defined target points in an interactive manner (as illustrated in Fig.1). This approach has led to the development of DragGAN, a novel framework comprising two core components:

Feature-Based Motion Supervision: This component guides handle points within the image toward their intended target positions through feature-based motion supervision.

Point Tracking: Leveraging discriminative GAN features, our new point tracking technique continuously localizes the position of handle points.

DragGAN empowers users to deform images with remarkable precision, enabling manipulation of the pose, shape, expression, and layout across diverse categories such as animals, cars, humans, landscapes, and more. These manipulations take place within the learned generative image manifold of a GAN, resulting in realistic outputs, even in complex scenarios like generating occluded content and deforming shapes while adhering to the object's rigidity.

Our comprehensive evaluations, encompassing both qualitative and quantitative comparisons, highlight DragGAN's superiority over existing methods in tasks related to image manipulation and point tracking. Additionally, we demonstrate its capabilities in manipulating real-world images through GAN inversion, showcasing its potential for various practical applications in the realm of visual content synthesis and control.