> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/automodel/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/automodel/_mcp/server.

# nemo_automodel.components.models.hunyuan_image3

## Submodules

* **[`nemo_automodel.components.models.hunyuan_image3.config`](/nemo-automodel/nemo_automodel/components/models/hunyuan_image3/config)**
* **[`nemo_automodel.components.models.hunyuan_image3.flow_adapter`](/nemo-automodel/nemo_automodel/components/models/hunyuan_image3/flow_adapter)**
* **[`nemo_automodel.components.models.hunyuan_image3.layers`](/nemo-automodel/nemo_automodel/components/models/hunyuan_image3/layers)**
* **[`nemo_automodel.components.models.hunyuan_image3.model`](/nemo-automodel/nemo_automodel/components/models/hunyuan_image3/model)**
* **[`nemo_automodel.components.models.hunyuan_image3.pipeline`](/nemo-automodel/nemo_automodel/components/models/hunyuan_image3/pipeline)**
* **[`nemo_automodel.components.models.hunyuan_image3.release`](/nemo-automodel/nemo_automodel/components/models/hunyuan_image3/release)**
* **[`nemo_automodel.components.models.hunyuan_image3.rope`](/nemo-automodel/nemo_automodel/components/models/hunyuan_image3/rope)**
* **[`nemo_automodel.components.models.hunyuan_image3.state_dict_adapter`](/nemo-automodel/nemo_automodel/components/models/hunyuan_image3/state_dict_adapter)**

## Package Contents

### Classes

| Name                                                                                                          | Description                                                                |
| ------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------- |
| [`HunyuanImage3Config`](#nemo_automodel-components-models-hunyuan_image3-config-HunyuanImage3Config)          | Configuration of the HunyuanImage-3.0 multimodal MoE transformer.          |
| [`HunyuanImage3ForCausalMM`](#nemo_automodel-components-models-hunyuan_image3-model-HunyuanImage3ForCausalMM) | HunyuanImage-3.0 transformer with the text-to-image flow-matching forward. |

### API

```python
class nemo_automodel.components.models.hunyuan_image3.config.HunyuanImage3Config(
    vocab_size: int = 133120,
    hidden_size: int = 4096,
    intermediate_size: int = 3072,
    moe_intermediate_size: int | list[int] = 3072,
    num_hidden_layers: int = 32,
    num_attention_heads: int = 32,
    num_key_value_heads: int = 8,
    attention_head_dim: int = 128,
    num_experts: int | list[int] = 64,
    moe_topk: int | list[int] = 8,
    num_shared_expert: int | list[int] = 1,
    use_mixed_mlp_moe: bool = True,
    norm_topk_prob: bool = True,
    router_aux_loss_coef: float = 0.0,
    hidden_act: str = 'silu',
    rms_norm_eps: float = 1e-05,
    rope_theta: float = 10000.0,
    use_qk_norm: bool = True,
    attention_bias: bool = False,
    mlp_bias: bool = False,
    max_position_embeddings: int = 22800,
    img_proj_type: str = 'unet',
    patch_size: int = 1,
    patch_embed_hidden_dim: int = 1024,
    image_base_size: int = 1024,
    image_token_id: int = 128006,
    timestep_token_id: int = 128017,
    vae: dict[str, typing.Any] | None = None,
    pad_token_id: int | None = 128009,
    bos_token_id: int | None = 127958,
    eos_token_id: int | list[int] | None = 127957,
    tie_word_embeddings: bool = False,
    torch_dtype: str = 'bfloat16',
    kwargs: typing.Any = {}
)
```

**Bases:** `PretrainedConfig`

Configuration of the HunyuanImage-3.0 multimodal MoE transformer.

Architecture (tencent/HunyuanImage-3.0):

* 32 decoder layers, hidden size 4096, GQA with 32 query / 8 KV heads, head dim 128
* Every layer is MoE: 64 routed experts (top-8, softmax, renormalized) plus one shared expert
* Per-head QK RMSNorm applied after RoPE; 2D RoPE over the joint text / image sequence
* Image tokens come from VAE latents through a UNet patch embedding, and the diffusion velocity is read out
  through a UNet final layer, both conditioned on the flow-matching timestep

**`head_dim`** `int`

---

**`keys_to_ignore_at_inference`** `= ['past_key_values']`

---

**`latent_channels`** `int`

---

**`model_type`** `= 'hunyuan_image_3_moe'`

---

**`vae`**

---

```python
class nemo_automodel.components.models.hunyuan_image3.model.HunyuanImage3ForCausalMM(
    config: nemo_automodel.components.models.hunyuan_image3.config.HunyuanImage3Config,
    moe_config: nemo_automodel.components.moe.config.MoEConfig | None = None,
    backend: nemo_automodel.components.models.common.BackendConfig | None = None,
    kwargs: typing.Any = {}
)
```

**Bases:** [HFCheckpointingMixin](/nemo-automodel/nemo_automodel/components/models/common/hf_checkpointing_mixin#nemo_automodel-components-models-common-hf_checkpointing_mixin-HFCheckpointingMixin), `Module`, [MoEFSDPSyncMixin](/nemo-automodel/nemo_automodel/components/moe/fsdp_mixin#nemo_automodel-components-moe-fsdp_mixin-MoEFSDPSyncMixin)

HunyuanImage-3.0 transformer with the text-to-image flow-matching forward.

`forward` predicts the flow velocity of noisy latents given the token sequence; `forward_text` returns
next-token logits (the release's `gen_text` mode) and is used for parity checks.

**`_keep_in_fp32_modules_strict`** `= ['mlp.gate']`

---

**`backend`** `= backend or BackendConfig()`

---

**`final_layer`**

---

**`lm_head`**

---

**`model`**

---

**`patch_embed`**

---

**`state_dict_adapter`**

---

**`tie_word_embeddings_support`** `TieSupport = TieSupport.UNTIED_ONLY`

---

**`time_embed`** `= TimestepEmbedder(hidden, dtype=dtype)`

---

**`time_embed_2`** `= TimestepEmbedder(hidden, dtype=dtype)`

---

**`timestep_emb`** `= TimestepEmbedder(hidden, dtype=dtype)`

---

```python
nemo_automodel.components.models.hunyuan_image3.model.HunyuanImage3ForCausalMM.forward(
    input_ids: torch.Tensor,
    latents: torch.Tensor,
    timestep: torch.Tensor,
    valid_lengths: torch.Tensor | None = None,
    return_dict: bool = False,
    kwargs: typing.Any = {}
) -> tuple[torch.Tensor] | dict[str, torch.Tensor]
```

Predict the flow velocity of the noisy latents.

**Parameters:**

**`input_ids`** `torch.Tensor`

`[batch, seq]` token ids laid out as described in the module docstring, right-padded.
Every row holds exactly `h*w` contiguous image tokens, preceded by the `<timestep>` token.

---

**`latents`** `torch.Tensor`

`[batch, channels, h, w]` noisy VAE latents.

---

**`timestep`** `torch.Tensor`

`[batch]` flow-matching timesteps in `[0, 1000]` (`sigma * 1000`).

---

**`valid_lengths`** `torch.Tensor | None` — default: None

`[batch]` number of non-padding tokens per row; defaults to the full length.

---

**`return_dict`** `bool` — default: False

Return `{"sample": velocity}` instead of `(velocity,)`.

---

**Returns:** `tuple[torch.Tensor] | dict[str, torch.Tensor]`

`[batch, channels, h, w]` predicted velocity, as a one-element tuple or a dict.

```python
nemo_automodel.components.models.hunyuan_image3.model.HunyuanImage3ForCausalMM.forward_text(
    input_ids: torch.Tensor
) -> torch.Tensor
```

Next-token logits of a causal text-only sequence (the release's `gen_text` mode).

**Parameters:**

**`input_ids`** `torch.Tensor`

Long tensor of shape \[batch, sequence].

---

**Returns:** `torch.Tensor`

fp32 tensor of shape \[batch, sequence, vocab].

```python
nemo_automodel.components.models.hunyuan_image3.model.HunyuanImage3ForCausalMM.from_config(
    config: nemo_automodel.components.models.hunyuan_image3.config.HunyuanImage3Config,
    moe_config: nemo_automodel.components.moe.config.MoEConfig | None = None,
    backend: nemo_automodel.components.models.common.BackendConfig | None = None,
    kwargs: typing.Any = {}
) -> 'HunyuanImage3ForCausalMM'
```

classmethod

```python
nemo_automodel.components.models.hunyuan_image3.model.HunyuanImage3ForCausalMM.from_pretrained(
    pretrained_model_name_or_path: str,
    model_args: typing.Any = (),
    kwargs: typing.Any = {}
) -> 'HunyuanImage3ForCausalMM'
```

classmethod

```python
nemo_automodel.components.models.hunyuan_image3.model.HunyuanImage3ForCausalMM.get_input_embeddings() -> torch.nn.Embedding
```

```python
nemo_automodel.components.models.hunyuan_image3.model.HunyuanImage3ForCausalMM.get_output_embeddings() -> torch.nn.Module
```

```python
nemo_automodel.components.models.hunyuan_image3.model.HunyuanImage3ForCausalMM.initialize_weights(
    buffer_device: torch.device | None = None,
    dtype: torch.dtype = torch.bfloat16
) -> None
```

```python
nemo_automodel.components.models.hunyuan_image3.model.HunyuanImage3ForCausalMM.update_moe_gate_bias() -> None
```