Ideogram’s Pro Tier: 12K AI Images Monthly
AI News Toronto-based startup Ideogram, emerging from a background steeped in Google Brain expertise, is intensifying competition in the AI image generation landscape. Amidst giants like Adobe and Meta, Ideogram has introduced a new subscription tier aimed at empowering its most demanding users—professional creators and active enthusiasts.
The new Pro tier, priced at $48 monthly when billed annually (or $60 on a monthly basis), expands Ideogram’s subscription options, which already include Free, Basic, and Plus levels. The Pro plan is designed to cater to high-volume needs, offering significant enhancements over the existing plans.
Key to the Pro tier is the capability for subscribers to submit up to 3,000 text prompts per month. These prompts receive prioritized processing, producing up to four images in less than 15 seconds each, totaling 12,000 fast-generated images monthly. This is a substantial increase compared to the 400 and 1,000 prompts offered in the Plus and Basic tiers, respectively.
A forthcoming feature set to enhance productivity further is the ability to upload prompts in bulk using CSV files. This innovation will allow users to bypass the current manual entry system, streamlining the image generation process significantly.
Despite its robust feature set, Ideogram’s imagery lacks indemnification for enterprise usage, a notable difference from services provided by larger firms like OpenAI and Adobe. This could affect users seeking to utilize these images in high-stakes commercial projects such as advertising or marketing. However, Ideogram’s terms of service do permit commercial use, and the platform uniquely offers stylized text and typography generation within images—a feature that is either absent or inconsistent in other AI image-generation tools.
This suite of features, particularly the enhanced capacity and speed of the Pro plan, positions Ideogram as a competitive choice for professionals in various industries seeking efficient and creative image-generation solutions. Subscriptions to the Ideogram Pro plan are available starting today. SOURCE
Meshy Celebrates One Year with Launch of Meshy-3: Elevating 3D Generative AI
AI News Today marks the first anniversary of Meshy, a milestone we’re celebrating with the release of Meshy-3, our latest and most advanced version yet. Meshy-3 introduces cutting-edge updates in text-to-3D conversion and debuts an innovative image-to-3D pipeline, setting a new standard in 3D generative AI technology.
Enhanced Text to 3D Features: Ultra Realism and Sculpture Style
Meshy-3’s Text to 3D now features ultra-realistic, high-poly model generation capabilities, ideal for high-end gaming and cinematic applications. The new ‘Sculpture’ style option allows creators to generate detailed models with photogrammetry quality, complete with mesh-generated displacement maps. These models are equipped with comprehensive PBR (Physically Based Rendering) textures, including displacement, normal, curvature, and AO maps, ensuring they are ready for direct integration into digital content creation tools and game engines.
Revolutionary PBR Texture Generation
Recognizing the challenges of utilizing AI-generated models under dynamic lighting conditions, Meshy-3 has enhanced its capability to produce PBR maps. This upgrade significantly improves the realism and detail of multi-material assets, providing a substantial improvement in visual fidelity across various lighting conditions.
Image to 3D Conversion: Vision to Creation
Meshy-3 also introduces a groundbreaking Image to 3D feature, designed to transform 2D images into 3D models with more natural shapes and clearer textures. This new pipeline bridges the gap between vision and creation, enabling artists and designers to bring their imaginations to life with unprecedented ease and precision.
Additional Innovations: Smart Healing and Prompt Helper
Meshy-3 includes several additional tools to enhance the user experience:
- Smart Healing: This tool automatically corrects common AI-induced texture anomalies, such as extra eyes or misplaced features, ensuring clean and realistic outputs.
- Prompt Helper: To aid users in crafting effective prompts, Meshy-3 offers a prompt library, simplifying the creation process and enhancing the overall user experience.
- Community Engagement: Meshy continues to foster a vibrant community of creators. With the new community badge system, users can earn recognition as they create and share their work, fostering a collaborative and supportive environment.
As we reflect on the past year and look forward to the future, we are committed to continuous innovation and community building. We extend our heartfelt thanks to our dedicated team and the enthusiastic Meshy community. Your creativity and feedback are what drive us to push the boundaries of what generative AI can achieve in 3D modeling. Stay tuned for more exciting updates from Meshy! SOURCE
OpenAI’s Unreleased Sora Model Debuts in Music Video
AI News OpenAI, known for pushing the boundaries of artificial intelligence, has introduced a cutting-edge AI model named Sora, designed to produce realistic, high-resolution videos up to 60 seconds long. Despite not being released to the public yet, Sora has already been put to use by a select group of artists and filmmakers, chosen by OpenAI to explore its capabilities and identify potential risks.
Paul Trillo, a writer and director granted early access to Sora, has utilized this technology to create the first official music video for the indie artist Washed Out (Ernest Weatherly Greene Jr.), featuring his new single “The Hardest Part.” The video, a visual treat, consists of a series of seamless, quick zoom shots that combine to give the illusion of one continuous zoom, showcasing the powerful capabilities of the Sora model.
Trillo shared on the social platform X that the concept for this video was envisioned a decade ago but was only now realized through the capabilities of AI. He detailed that the final video was crafted from 55 clips selected from a total of 700, all stitched together using Adobe Premiere, demonstrating the potential of AI to transform the creative process in filmmaking.
Additionally, Adobe has expressed interest in integrating Sora and similar AI video generators into its Premiere Pro software, though no specific timeline for this integration has been provided. This move would streamline the video editing process but, until then, creators must rely on other third-party software for generating and importing AI-enhanced video clips.
In an interview with the Los Angeles Times, Washed Out discussed his excitement about incorporating such novel technology into his artistic vision, emphasizing the innovative potential of AI in shaping future multimedia projects. He also highlighted the detailed nature of the prompts used to guide the AI in video generation, pointing to a meticulous process that blends creative vision with technological precision.
This pioneering use of Sora not only marks a significant advancement in AI-driven media creation but also sparks discussions about the ethical implications of such technology. While it offers new avenues for artistic expression, there is an ongoing debate about the potential for AI to infringe on the rights and creations of human artists. Despite these concerns, the deployment of Sora in projects like Trillo’s music video illustrates a growing trend among creatives to embrace AI tools to push the boundaries of storytelling and visual artistry.SOURCE
Conclusion
AI News As we witness the groundbreaking advancements in AI technology—from Ideogram’s innovative subscription models enhancing image generation for professional creators to Meshy-3’s transformation of 3D modeling, and OpenAI’s Sora shaping the future of video production—it’s clear that the landscape of digital creation is rapidly evolving. These developments not only enhance the capabilities of creators across various media but also open up discussions about the ethical implications and potential of AI in creative industries. As AI News continues to push the boundaries of what’s possible, it invites us to reimagine the future of art, design, and interaction.
For more insights and the latest developments in AI technology, follow Arcot Group for continuous updates on how artificial intelligence is revolutionizing industries and empowering creators around the world.
