MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines
Paper • 2603.06679 • Published • 6
AI & ML interests
None defined yet.
Recent Activity
View all activity
akhaliq
submitted a
paper to Daily Papers 18 days ago
akhaliq
submitted a
paper to Daily Papers 25 days ago
akhaliq
submitted 2
papers to Daily Papers about 1 month ago
akhaliq
submitted a
paper to Daily Papers 2 months ago
akhaliq
submitted 3
papers to Daily Papers 3 months ago
akhaliq
submitted 3
papers to Daily Papers 3 months ago
V-DPM: 4D Video Reconstruction with Dynamic Point Maps
Paper • 2601.09499 • Published • 11
UM-Text: A Unified Multimodal Model for Image Understanding
Paper • 2601.08321 • Published • 12
ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation
Paper • 2601.03955 • Published • 3
akhaliq
submitted 5
papers to Daily Papers 4 months ago
FlowBlending: Stage-Aware Multi-Model Sampling for Fast and High-Fidelity Video Generation
Paper • 2512.24724 • Published • 9
Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow
Paper • 2512.24766 • Published • 9
What matters for Representation Alignment: Global Information or Spatial Structure?
Paper • 2512.10794 • Published • 9
Towards a Science of Scaling Agent Systems
Paper • 2512.08296 • Published • 17
ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models
Paper • 2512.07843 • Published • 22
elismasilva
posted an update 5 months ago
Post
473
Hey everyone,
I've built and deployed Panorama FLUX, a Gradio app for creating ultra-wide panoramic images from three different text prompts using the FLUX.1-schnell model.
It uses a custom "Mixture of Diffusers" pipeline to generate and seamlessly blend each section of the image.
Key Features:
- Multi-Prompt Input: Control the left, center, and right of the scene with unique prompts.
- Seamless Blending: Choose between Cosine and Gaussian blending methods to eliminate seams between tiles.
- Optimized for FLUX.1-schnell: Designed for fast, 4-step generation with embedded guidance.
- Multi-Language Support: On-the-fly translation for prompts written in Korean and Chinese.
- Memory Efficient: Supports both custom (mmgp) and standard diffusers offloading for use on consumer GPUs or in Spaces.
This was a fun project that involved deep-diving into the FLUX architecture to get the tiling, guidance, and positional embeddings right.
Try it out!
🚀 Live Demo on Hugging Face Spaces:
elismasilva/flux-1-panorama
I've built and deployed Panorama FLUX, a Gradio app for creating ultra-wide panoramic images from three different text prompts using the FLUX.1-schnell model.
It uses a custom "Mixture of Diffusers" pipeline to generate and seamlessly blend each section of the image.
Key Features:
- Multi-Prompt Input: Control the left, center, and right of the scene with unique prompts.
- Seamless Blending: Choose between Cosine and Gaussian blending methods to eliminate seams between tiles.
- Optimized for FLUX.1-schnell: Designed for fast, 4-step generation with embedded guidance.
- Multi-Language Support: On-the-fly translation for prompts written in Korean and Chinese.
- Memory Efficient: Supports both custom (mmgp) and standard diffusers offloading for use on consumer GPUs or in Spaces.
This was a fun project that involved deep-diving into the FLUX architecture to get the tiling, guidance, and positional embeddings right.
Try it out!
🚀 Live Demo on Hugging Face Spaces:
elismasilva/flux-1-panorama
owenkaplinsky
posted an update 5 months ago
Post
346
I built MCP Blockly for MCP's 1st Birthday hackathon: a full visual environment for creating real MCP servers with block based logic. Research shows that learners develop stronger understanding when they work hands on, so the goal here is to make MCP development something you can explore directly rather than only read about.
Under the hood, every block on the canvas is converted into live Python through a custom generator that rebuilds your MCP function signature, parameters, and logic on each edit. The AI assistant reads the entire workspace through a structured representation, plans multi step changes, creates and adjusts blocks, tests your tool with real inputs, and can even deploy the finished MCP server to your Hugging Face account.
Video:
https://www.youtube.com/watch?v=5oj-2uIZpb0
Try it out:
MCP-1st-Birthday/MCP-Blockly
Under the hood, every block on the canvas is converted into live Python through a custom generator that rebuilds your MCP function signature, parameters, and logic on each edit. The AI assistant reads the entire workspace through a structured representation, plans multi step changes, creates and adjusts blocks, tests your tool with real inputs, and can even deploy the finished MCP server to your Hugging Face account.
Video:
https://www.youtube.com/watch?v=5oj-2uIZpb0
Try it out:
MCP-1st-Birthday/MCP-Blockly