HiDream I1

HiDream is a large image generation foundation model with 17B parameters.

HiDream-I1 consists of 3 variants:
- Full
- Dev
- Fast

The main difference between variants is recommended step count:
- full=50, dev=28, fast=16

HiDream-I1 is compatible with:
- FlowMatching Samplers
- Remote VAE feature
- TAE Live-preview feature

Important

Due to its size (over 25B params in 58GB), offloading and on-the-fly quantization are generally required.
Running HiDream on GPUs with under 16GB VRAM is possible with BnB-NF4 or Quanto-Int4 quantization and default Balanced offload settings.
Note that you must pick quantization methods that are compatible with your GPU and platform

[!NOTE] Set an appropriate offloading mode before loading the model to avoid out-of-memory errors.
For more information see Offloading Wiki

[!NOTE] Check compatibility of different quantization methods with your platform and GPU.
For more information see Quantization Wiki

[!IMPORTANT] Use reference models
Simply select it from Networks -> Models -> Reference
and the model will be auto-downloaded on first use.

Location of downloaded model is: - hugginface folder is used for individual components: transformers, T5 text encoder, and llama LLM - diffusers folder is used for the main model Exact location of both folders is shown in Settings -> System Paths.

Warning

Manually downloaded models in either safetensors or gguf formats are currently not supported.

[!IMPORTANT] Llama-3.1-8b-instruct LLM model used by HiDream is a gated model!
You need to request access from the authors to use it.
See Gated Wiki for more information

Text Encoders

HiDream uses 4 text encoders: clip-l, clip-g, t5-1.1-xxl, llama-3.1-8b-instruct for a total of 8.3B parameters.

Custom llama model can be set in: Settings -> Model options -> HiDream

Note

SD.Next implementation differs from the reference by increasing default max token length from 128 to 256.
Max token length can be further overridden using environment variable HIDREAM_MAX_SEQUENCE_LENGTH.