πŸ‘οΈ8,962
GitHubLinkedIn
AI Holodeck and Virtual Worldsβ€’β€’6 min readβ€’1112 words

✨ Draw Things - Multi-Image Editing

πŸ‘οΈ0reads (human + AI)πŸ€–0AI ingestions

✨ Draw Things - Multi-Image Editing

This article details the multi-image editing capabilities within Draw Things 2509, explaining how users can manage and assign multiple images for creative projects. It outlines the process of utilizing a moodboard for image organization and integration.

Key Points:

β€’ Organize and manage multiple images efficiently using a moodboard.

β€’ Assign specific roles to images from the moodboard for editing.

β€’ Utilize the canvas image as the primary input for operations.

β€’ Streamline complex image manipulation workflows.

πŸš€ Implementation:

  1. Populate Moodboard: Add desired images to the moodboard panel.
  2. Identify Image Order: Images are numbered left to right in the moodboard.
  3. Use Canvas Image: The image on the canvas acts as the first picture in the sequence.
  4. Integrate Moodboard Images: Subsequent images in the moodboard correspond to higher picture numbers.

πŸ”— Resources:

β€’ Draw Things β†— - Learn more about the image editing application

Image

Image


πŸ€– AI Innovation - European LLM Day

This article summarizes the JΓΌlich LLM Day, an event that convened over 50 experts to showcase European advancements in AI innovation, particularly focusing on Large Language Models. It highlights the collaborative efforts between research, industry, and education.

Key Points:

β€’ Fosters collaboration across research, industry, and education sectors.

β€’ Demonstrates advancements in Large Language Model technologies.

β€’ Highlights Europe's contributions to global AI innovation.

β€’ Brings together a diverse group of over 50 AI experts.

πŸ”— Resources:

β€’ DeepL β†— - Discover more about European AI and language solutions

Image

Image


Image

Image


Image

Image


πŸ€– AI Models - Reve V1 Image Editing Performance

This article announces the debut of Reve V1, Reve AI's first image editing model, which achieved a significant third-place ranking in the Artificial Analysis Image Editing Leaderboard. It details the model's foundation and capabilities.

Key Points:

β€’ Achieves a top-tier ranking in image editing performance benchmarks.

β€’ Represents Reve AI's inaugural image editing model.

β€’ Leverages advanced text-to-image foundation technology.

β€’ Supports both diverse image editing functionalities.

πŸ”— Resources:

β€’ Reve AI β†— - Explore more about Reve AI's image editing capabilities

β€’ Artificial Analysis β†— - Review AI model performance leaderboards

Image

Image


πŸ’‘ AI Video - Networking Event

This article announces an upcoming happy hour event in San Francisco, co-hosted by AI Affogato and Fal, focusing on discussions around the latest in AI video technology. Attendees will have opportunities to network and explore topics like Sora 2.

Key Points:

β€’ Provides a platform for discussing AI video advancements.

β€’ Facilitates networking among industry professionals.

β€’ Includes discussions on cutting-edge topics like Sora 2.

β€’ Offers an opportunity for community engagement in AI video.

πŸ”— Resources:

β€’ AI Affogato β†— - Follow for AI video insights and events

β€’ Fal β†— - Discover AI services and collaborations

β€’ Techweek β†— - Learn about technology events

Image

Image


πŸ€– Multimodal AI - Liquid Foundation Models

This article introduces Liquid AI's new line of omni Liquid foundation models, designed to push Chinchilla scaling laws for multimodal AI. It highlights their integrated speech capabilities, low latency, and high inference speed.

Key Points:

β€’ Integrates speech-to-speech, text-to-speech, and automatic speech recognition in one model.

β€’ Achieves sub-100ms latency for real-time applications.

β€’ Delivers over 10x faster inference speed compared to alternatives.

β€’ Built upon the efficient LFM v2 architecture.

β€’ Demonstrates strong performance with a 56.8 VoiceBench score.

πŸ”— Resources:

β€’ LiquidAI β†— - Explore multimodal foundation models and technology

β€’ Ramin M H β†— - Follow updates from LiquidAI's leadership

Image

Image


✨ Draw Things - Qwen Image Edit 2509 Integration

This article announces the release of Draw Things version 1.20250930.0 for iOS and macOS, which introduces support for Qwen Image Edit 2509. The update also includes fixes for network connectivity issues on iOS 26 Cloud Compute.

Key Points:

β€’ Introduces integration with Qwen Image Edit 2509 for enhanced capabilities.

β€’ Resolves network connectivity issues for Cloud Compute on iOS 26.

β€’ Marks the debut of Qwen's image editing features within the app.

β€’ Available on iOS and macOS App Stores.

πŸ”— Resources:

β€’ Draw Things β†— - Get the latest update for image editing features

Image

Image


πŸš€ Metaverse - RadNFTV Decentraland Partnership

This article announces a strategic partnership between RadNFTV and Decentraland, aimed at enhancing streaming, sharing, and celebration experiences within the metaverse. It highlights new opportunities for users and upcoming events.

Key Points:

β€’ Creates new opportunities for content streaming and sharing.

β€’ Enhances communal event experiences in Decentraland.

β€’ Prepares for upcoming events like Fright Night and Music Festival 2025.

β€’ Encourages new user engagement with the Decentraland platform.

πŸ”— Resources:

β€’ RadNFTV β†— - Explore new streaming experiences in the metaverse

β€’ Decentraland β†— - Discover the virtual world platform

Image

Image


πŸ’‘ Company Leadership - DeepL Appoints New CPO

This article announces the appointment of GonΓ§alo Gaiolas as DeepL's new Chief Product Officer. His role will involve leading the development of new innovations, including DeepL Agent, and advancing their market-leading Language AI solutions.

Key Points:

β€’ Drives the development of new products such as DeepL Agent.

β€’ Advances market-leading Language AI solutions.

β€’ Strengthens the senior leadership team.

β€’ Aims to accelerate future innovations at DeepL.

πŸ”— Resources:

β€’ DeepL β†— - Learn more about DeepL's AI and leadership

Image

Image


✨ AI Video Generation - Wondercraft AI Sora 2 Integration

This article outlines Wondercraft AI's ongoing discussions with OpenAI to secure API access to Sora 2. The goal is to establish Wondercraft AI as a premier platform for long-form content creation utilizing Sora 2, including multimodal capabilities.

Key Points:

β€’ Secures early access to the OpenAI Sora 2 API.

β€’ Positions Wondercraft AI as a leading platform for Sora 2 utilization.

β€’ Enables multi-modal long-form content creation, including music and voice.

β€’ Streamlines the process of generating complex AI-driven media.

πŸ”— Resources:

β€’ Wondercraft AI β†— - Explore AI tools for content creation

β€’ OpenAI β†— - Discover leading AI research and APIs


πŸ’‘ Product Development - Aug Imagination Updates

This article summarizes Aug Imagination's recent product development progress, highlighted in their latest podcast. Key achievements include hiring a new front-end developer, creating an interface prototype, and discussing advancements in Adobe technologies.

Key Points:

β€’ Recruits a front-end developer for the SuperModels project.

β€’ Develops an interface prototype for internal testing and refinement.

β€’ Discusses insights and advancements in Adobe technologies.

β€’ Continues active product development during a content break.

πŸ”— Resources:

β€’ Aug Imagination β†— - Follow for product updates and podcasts

Image

Image


⭐️ Support

If you liked reading this report, please star ⭐️ this repository and follow me on Github β†—, 𝕏 (previously known as Twitter) β†— to help others discover these resources and regular updates.


Related AI Holodeck and Virtual Worlds Breakdowns

Drix10
Written by Drix10

Co founder @ PartPilot | 1 x Acquired Founder | Canopy @ f.inc | Cybersec @ DSU | 2x International Hackathon πŸ†. Read more on drix10.com.