{"work":{"id":"68d4c0f7-3dfd-438d-a823-6a93fd0a835d","openalex_id":null,"doi":null,"arxiv_id":"2505.22705","raw_key":null,"title":"HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer","authors":null,"authors_text":"Qi Cai, Jingwen Chen, Yang Chen, Yehao Li, Fuchen Long, Yingwei Pan","year":2025,"venue":"cs.CV","abstract":"Recent advancements in image generative foundation models have prioritized quality improvements but often at the cost of increased computational complexity and inference latency. To address this critical trade-off, we introduce HiDream-I1, a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds. HiDream-I1 is constructed with a new sparse Diffusion Transformer (DiT) structure. Specifically, it starts with a dual-stream decoupled design of sparse DiT with dynamic Mixture-of-Experts (MoE) architecture, in which two separate encoders are first involved to independently process image and text tokens. Then, a single-stream sparse DiT structure with dynamic MoE architecture is adopted to trigger multi-model interaction for image generation in a cost-efficient manner. To support flexiable accessibility with varied model capabilities, we provide HiDream-I1 in three variants: HiDream-I1-Full, HiDream-I1-Dev, and HiDream-I1-Fast.\n  Furthermore, we go beyond the typical text-to-image generation and remould HiDream-I1 with additional image conditions to perform precise, instruction-based editing on given images, yielding a new instruction-based image editing model namely HiDream-E1. Ultimately, by integrating text-to-image generation and instruction-based image editing, HiDream-I1 evolves to form a comprehensive image agent (HiDream-A1) capable of fully interactive image creation and refinement. To accelerate multi-modal AIGC research, we have open-sourced all the codes and model weights of HiDream-I1-Full, HiDream-I1-Dev, HiDream-I1-Fast, HiDream-E1 through our project websites: https://github.com/HiDream-ai/HiDream-I1 and https://github.com/HiDream-ai/HiDream-E1. All features can be directly experienced via https://vivago.ai/studio.","external_url":"https://arxiv.org/abs/2505.22705","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-22T09:34:46.711139+00:00","pith_arxiv_id":"2505.22705","created_at":"2026-05-08T18:28:57.540489+00:00","updated_at":"2026-05-22T09:34:46.711139+00:00","title_quality_ok":true,"display_title":"HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer","render_title":"HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer"},"hub":{"state":{"work_id":"68d4c0f7-3dfd-438d-a823-6a93fd0a835d","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":25,"external_cited_by_count":null,"distinct_field_count":4,"first_pith_cited_at":"2025-08-04T11:49:20+00:00","last_pith_cited_at":"2026-05-21T15:57:04+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-05-30T18:21:24.575591+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"baseline","n":11},{"context_role":"background","n":3},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"baseline","n":11},{"context_polarity":"background","n":3},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}