gen‑ai.news
← Back
Image

Ideogram says its new model can edit part of an image without messing up the rest

Ideogram says its new model can edit part of an image without messing up the rest

Ideogram has launched Ideogram 4.5, its latest image generation and editing model, with a focus on a persistent challenge in AI image editing - making changes to one part of an image without inadvertently altering the rest. Maintaining consistency in unedited regions has long been a weak point for diffusion-based models, which tend to reinterpret the entire image during generation rather than isolating only the targeted area.

The model ships with native 2K resolution output, which puts it above many competitors that require separate upscaling steps to reach comparable quality. Pricing starts at 0.8 cents per image, positioning it as a practical option for developers and teams building image-heavy products rather than just individual creators.

On the integration side, Runway, Pika, and Leonardo AI are listed as early partners, suggesting the model is being designed with third-party workflows in mind from the start. These platforms span video generation and creative tooling, so Ideogram 4.5 could end up embedded in a fairly wide range of production pipelines relatively quickly.

Ideogram has also confirmed that an open-weight release is planned, which would allow developers to run and fine-tune the model outside of Ideogram's own platform. That detail is likely to matter to teams with specific deployment or data-privacy requirements, and it broadens the potential use cases well beyond what a closed API alone would support.

Enjoy this story? Get the next one in your inbox.

Twice a week: the most important stories in generative image and video AI, distilled into a 2-minute read.

Free. Unsubscribe any time. No spam, ever.

Your next read

You can now generate and edit GIFs with ChatGPT - here's how
Image

You can now generate and edit GIFs with ChatGPT - here's how

OpenAI has added GIF generation and editing to ChatGPT, giving users a way to create short animated images directly within the chat interface. The feature expands on the platform's existing image capabilities, extending them into the animated format. Here is what you need to know to get started.

Maket launches floor and wall textures from text or images
Image

Maket launches floor and wall textures from text or images

Maket, an AI-assisted architectural design tool, has added the ability to generate floor and wall textures directly from text prompts or reference images. The feature gives designers a faster way to explore material options within their existing workflow. It represents a natural expansion of Maket's generative toolset into the domain of surface and finish design.

AI Ambition: ArtCraft Cloned Photoshop and Now Wants to "Rebuild Everything"
Image

AI Ambition: ArtCraft Cloned Photoshop and Now Wants to "Rebuild Everything"

ArtCraft made waves by using AI to build an open-source reimagining of Photoshop, and CEO Brandon Thomas says that is only the beginning. The company's broader ambition is to challenge the closed, proprietary systems that dominate creative software and the web. It is a bold long-term goal, rooted in the idea that AI can lower the barrier to rebuilding complex software from scratch.