Diffusion Model Websites
MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-
AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners.
Not Applicable
$
8.94
AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners.
Not Applicable
$
8.94
SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstracti
SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution.
Not Applicable
$
8.94
Sin3DM
A diffusion model learned from a single 3D textured shape.
Not Applicable
$
8.94
Neta Lumina - Next-Generation Anime-Style Image Generation
An advanced anime-style image generation model developed by Neta.art Lab, built on Lumina-Image-2.0 with powerful multilingual support.
Not Applicable
$
8.94
Wan 2.2 - Next-Gen AI Video Generation Model | Beyond Sora Technology
Wan 2.2 is the latest AI video generation model featuring innovative diffusion techniques and advanced architecture, delivering video quality and efficiency beyond Sora. Supports multiple resolutions, long-form video generation, and precise motion control.
Not Applicable
$
8.94
Qwen Image - AI Image Generator with Text Rendering
Qwen Image: 20B MMDiT AI model for image generation with superior text rendering. Create stunning visuals with precise Chinese and English text.
Not Applicable
$
8.94
Qwen-Image: Revolutionary 20B Parameter AI Image Generation Model | Al
Qwen-Image is a 20 billion parameter multimodal AI image generation model open-sourced by Alibaba Cloud's Qwen team. Achieving SOTA performance in Chinese text rendering, image editing, and AI API capabilities. Apache 2.0 license.
Not Applicable
$
8.94
Wan2.2 - Open Source MoE Video Generation | Every Shot, Wan Take | wan
Wan2.2: World's first open-source MoE video generation model with cinematic control. Text-to-video, image-to-video at 720P. Download now on GitHub.
Not Applicable
$
8.94
