Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · HiDream-ai

HiDream-I1-Dev

HiDream-I1-Dev is a 17.11B-parameter text-to-image model from HiDream-ai. According to the model card, it is the distilled dev variant of the HiDream-I1 foundation family.

Publisher
HiDream-ai
Task
text-to-image
Model type
Unknown
License
mit
Library
diffusers
Publication status
Accepted · not indexed

Model overview

HiDream-I1-Dev is published by HiDream-ai as a text-to-image model. Captured Safetensors metadata reports 17,105,733,184 parameters, about 17.11B. According to the model card, HiDream-I1 is an open-source image foundation model with 17B parameters, with a technical report on its sparse diffusion transformer design.

Recorded capabilities

Distilled dev inference path

According to the model card, HiDream-I1 is a 17B-parameter foundation model and the inference script exposes full, dev, and fast model types.

Publisher-reported prompt-following tables

According to the model card, the publisher claims industry-leading GenEval and DPG scores and publishes DPG-Bench, GenEval, and HPSv2.1 comparison tables.

Documented diffusers workflow

According to the model card, generation uses the repository inference script and a Gradio demo, with automatic download of Meta-Llama-3.1-8B-Instruct files.

Split component licensing

According to the model card, Transformer models are MIT-licensed while the VAE comes from FLUX.1 schnell and text encoders carry Apache 2.0 and Llama 3.1 Community terms.

Use cases in the source record

  • Text-to-image generation using the card's dev-mode inference script and Gradio demo for interactive use.
  • Prompt-following evaluation study referencing the card's published DPG-Bench, GenEval, and HPSv2.1 tables for the HiDream-I1 family.

Limitations and unknowns

  • No independently measured evaluation results were extracted; benchmark tables are publisher-reported card claims.
  • No training data, compute, or hyperparameter detail was extracted from this record.
  • Component use requires following the VAE and text-encoder license terms stated in the card, not only the Transformer MIT terms.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: HiDream-ai/HiDream-I1-Dev

Captured: Unknown. Processed: 2026-09-07T19:35:06.269395+00:00.

HiDream-I1 is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds. For more features and to experience the full capabilities of our product, please visit https://vivago.ai/ . Project Updates 📝 May 28, 2025 : We've released our technical report HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer . 🚀 April 28, 2025 : We've open-sourced the instruction-based-image-editing model HiDream-E1-Full . Experience at https://huggingface.co/spaces/HiDream-ai/HiDream-E1-Full !. Key Features ✨ Superior Image Qu…

F001F002F003F004F005F006F008F009F011F013F015F016F017F018F019F020