theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-18 22:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1243 from modelscope/research_tutorial_1

Browse Source 
add research tutorial sec 1
This commit is contained in:
Zhongjie Duan
2026-02-02 14:29:39 +08:00
committed by GitHub
parent b4f6a4de6c 98ab238340
commit 21a6eb8e2f
10 changed files with 1679 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
diffsynth/configs/model_configs.py
View File

@@ -589,6 +589,14 @@ z_image_series = [
"model_class": "diffsynth.models.z_image_image2lora.ZImageImage2LoRAModel",
"extra_kwargs": {"compress_dim": 128},
},
{
# Example: ModelConfig(model_id="Qwen/Qwen3-0.6B", origin_file_pattern="model.safetensors")
"model_hash": "1392adecee344136041e70553f875f31",
"model_name": "z_image_text_encoder",
"model_class": "diffsynth.models.z_image_text_encoder.ZImageTextEncoder",
"extra_kwargs": {"model_size": "0.6B"},
"state_dict_converter": "diffsynth.utils.state_dict_converters.z_image_text_encoder.ZImageTextEncoderStateDictConverter",
},
]
MODEL_CONFIGS = qwen_image_series + wan_series + flux_series + flux2_series + z_image_series

30
diffsynth/models/z_image_text_encoder.py
View File

@@ -6,6 +6,36 @@ class ZImageTextEncoder(torch.nn.Module):
def __init__(self, model_size="4B"):
super().__init__()
config_dict = {
"0.6B": Qwen3Config(**{
"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": 1024,
"initializer_range": 0.02,
"intermediate_size": 3072,
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_scaling": None,
"rope_theta": 1000000,
"sliding_window": None,
"tie_word_embeddings": True,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.0",
"use_cache": True,
"use_sliding_window": False,
"vocab_size": 151936
}),
"4B": Qwen3Config(**{
"architectures": [
"Qwen3ForCausalLM"