support z image (#213)

* support z image

* Update diffsynth_engine/configs/pipeline.py

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

---------

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

Author: Glaceon-Hyy

diffsynth_engine/__init__.py

@@ -6,11 +6,13 @@
     WanSpeech2VideoPipelineConfig,
     QwenImagePipelineConfig,
     HunyuanPipelineConfig,
+    ZImagePipelineConfig,
     SDStateDicts,
     SDXLStateDicts,
     FluxStateDicts,
     WanStateDicts,
     QwenImageStateDicts,
+    ZImageStateDicts,
     AttnImpl,
     SpargeAttentionParams,
     VideoSparseAttentionParams,
@@ -55,11 +57,13 @@
     "WanSpeech2VideoPipelineConfig",
     "QwenImagePipelineConfig",
     "HunyuanPipelineConfig",
+    "ZImagePipelineConfig",
     "SDStateDicts",
     "SDXLStateDicts",
     "FluxStateDicts",
     "WanStateDicts",
     "QwenImageStateDicts",
+    "ZImageStateDicts",
     "AttnImpl",
     "SpargeAttentionParams",
     "VideoSparseAttentionParams",

diffsynth_engine/conf/models/z_image/qwen3_config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}