HiDream-I1: 17B Open Source Text-to-Image Model by HiDream-ai
ComfyUI Wiki
HiDream-I1 is a 17B parameter text-to-image model by HiDream-ai, combining DiT with MoE architecture. MIT licensed, available in Full/Dev/Fast variants.
H
HiDream-I1 by HiDream-ai
Text-to-ImageOpen SourceDiTMoEOpen-source 17B parameter text-to-image model combining DiT with MoE (Mixture of Experts) architecture. MIT licensed. Integrates four text encoders (OpenCLIP ViT-bigG, CLIP ViT-L, T5, LLaMA 3.1 8B). Available in Full (50 steps), Dev (28 steps), and Fast (16 steps) variants, with fp8/GGUF/nf4 community versions.
| Developer | HiDream-ai |
| Release Date | 2025-04-07 |
| Architecture | DiT + MoE (17B parameters) |
| License | MIT |
| Text Encoders | OpenCLIP ViT-bigG, CLIP ViT-L, T5XXL, LLaMA 3.1 8B |
| Variants | Full (50 steps), Dev (28 steps), Fast (16 steps) |
| Community Variants | fp8, GGUF (city96), nf4 (azaneko) |
Models
| Model | Description | License | Released |
|---|---|---|---|
| HiDream-O1-Image | 8B UiT T2I + editing + personalization; BF16/FP8/MXFP8 | MIT | 2026-05 |
Select a model above for curated weight downloads, tutorials, and related information.
Comments
Sign in with GitHub to join the discussion.