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 branch 'main' into ltx-2

Browse Source
This commit is contained in:
Zhongjie Duan
2026-02-03 13:06:44 +08:00
committed by GitHub
parent 49bc84f78e a781138413
commit 25c3a3d3e2
34 changed files with 2132 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
diffsynth/models/model_loader.py
View File

@@ -29,7 +29,7 @@ class ModelPool:
module_map = None
return module_map
def load_model_file(self, config, path, vram_config, vram_limit=None):
def load_model_file(self, config, path, vram_config, vram_limit=None, state_dict=None):
model_class = self.import_model_class(config["model_class"])
model_config = config.get("extra_kwargs", {})
if "state_dict_converter" in config:
@@ -43,6 +43,7 @@ class ModelPool:
state_dict_converter,
use_disk_map=True,
vram_config=vram_config, module_map=module_map, vram_limit=vram_limit,
state_dict=state_dict,
)
return model
@@ -59,7 +60,7 @@ class ModelPool:
}
return vram_config
def auto_load_model(self, path, vram_config=None, vram_limit=None, clear_parameters=False):
def auto_load_model(self, path, vram_config=None, vram_limit=None, clear_parameters=False, state_dict=None):
print(f"Loading models from: {json.dumps(path, indent=4)}")
if vram_config is None:
vram_config = self.default_vram_config()
@@ -67,7 +68,7 @@ class ModelPool:
loaded = False
for config in MODEL_CONFIGS:
if config["model_hash"] == model_hash:
model = self.load_model_file(config, path, vram_config, vram_limit=vram_limit)
model = self.load_model_file(config, path, vram_config, vram_limit=vram_limit, state_dict=state_dict)
if clear_parameters: self.clear_parameters(model)
self.model.append(model)
model_name = config["model_name"]

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"