refine code

README.md

@@ -101,7 +101,8 @@ image.save("image.jpg")
 |[FLUX.1-dev-LoRA-Fusion-Preview](https://modelscope.cn/models/DiffSynth-Studio/LoRAFusion-preview-FLUX.1-dev)||[code](./examples/flux/model_inference/FLUX.1-dev-LoRA-Fusion.py)|-|-|-|-|-|
 |[Step1X-Edit](https://www.modelscope.cn/models/stepfun-ai/Step1X-Edit)|`step1x_reference_image`|[code](./examples/flux/model_inference/Step1X-Edit.py)|[code](./examples/flux/model_inference_low_vram/Step1X-Edit.py)|[code](./examples/flux/model_training/full/Step1X-Edit.sh)|[code](./examples/flux/model_training/validate_full/Step1X-Edit.py)|[code](./examples/flux/model_training/lora/Step1X-Edit.sh)|[code](./examples/flux/model_training/validate_lora/Step1X-Edit.py)|
 |[FLEX.2-preview](https://www.modelscope.cn/models/ostris/Flex.2-preview)|`flex_inpaint_image`, `flex_inpaint_mask`, `flex_control_image`, `flex_control_strength`, `flex_control_stop`|[code](./examples/flux/model_inference/FLEX.2-preview.py)|[code](./examples/flux/model_inference_low_vram/FLEX.2-preview.py)|[code](./examples/flux/model_training/full/FLEX.2-preview.sh)|[code](./examples/flux/model_training/validate_full/FLEX.2-preview.py)|[code](./examples/flux/model_training/lora/FLEX.2-preview.sh)|[code](./examples/flux/model_training/validate_lora/FLEX.2-preview.py)|
-|[Nexus-Gen-Edit](https://www.modelscope.cn/models/DiffSynth-Studio/Nexus-GenV2)|`nexus_gen_reference_image`|[code](./examples/flux/model_inference/Nexus-Gen-Editing.py)|[code](./examples/flux/model_inference_low_vram/Nexus-Gen-Editing.py)|[code](./examples/flux/model_training/full/FLUX.1-NexusGen-Edit.sh)|[code](./examples/flux/model_training/validate_full/Nexus-Gen-Editing.py)|[code](./examples/flux/model_training/lora/FLUX.1-NexusGen-Edit.sh)|[code](./examples/flux/model_training/validate_lora/Nexus-Gen-Editing.py)|
+|[Nexus-Gen](https://www.modelscope.cn/models/DiffSynth-Studio/Nexus-GenV2)|`nexus_gen_reference_image`|[code](./examples/flux/model_inference/Nexus-Gen-Editing.py)|[code](./examples/flux/model_inference_low_vram/Nexus-Gen-Editing.py)|[code](./examples/flux/model_training/full/Nexus-Gen.sh)|[code](./examples/flux/model_training/validate_full/Nexus-Gen.py)|[code](./examples/flux/model_training/lora/Nexus-Gen.sh)|[code](./examples/flux/model_training/validate_lora/Nexus-Gen.py)|
+
 </details>
 
 

README_zh.md

@@ -103,7 +103,8 @@ image.save("image.jpg")
 |[FLUX.1-dev-LoRA-Fusion-Preview](https://modelscope.cn/models/DiffSynth-Studio/LoRAFusion-preview-FLUX.1-dev)||[code](./examples/flux/model_inference/FLUX.1-dev-LoRA-Fusion.py)|-|-|-|-|-|
 |[Step1X-Edit](https://www.modelscope.cn/models/stepfun-ai/Step1X-Edit)|`step1x_reference_image`|[code](./examples/flux/model_inference/Step1X-Edit.py)|[code](./examples/flux/model_inference_low_vram/Step1X-Edit.py)|[code](./examples/flux/model_training/full/Step1X-Edit.sh)|[code](./examples/flux/model_training/validate_full/Step1X-Edit.py)|[code](./examples/flux/model_training/lora/Step1X-Edit.sh)|[code](./examples/flux/model_training/validate_lora/Step1X-Edit.py)|
 |[FLEX.2-preview](https://www.modelscope.cn/models/ostris/Flex.2-preview)|`flex_inpaint_image`, `flex_inpaint_mask`, `flex_control_image`, `flex_control_strength`, `flex_control_stop`|[code](./examples/flux/model_inference/FLEX.2-preview.py)|[code](./examples/flux/model_inference_low_vram/FLEX.2-preview.py)|[code](./examples/flux/model_training/full/FLEX.2-preview.sh)|[code](./examples/flux/model_training/validate_full/FLEX.2-preview.py)|[code](./examples/flux/model_training/lora/FLEX.2-preview.sh)|[code](./examples/flux/model_training/validate_lora/FLEX.2-preview.py)|
-|[Nexus-Gen-Edit](https://www.modelscope.cn/models/DiffSynth-Studio/Nexus-GenV2)|`nexus_gen_reference_image`|[code](./examples/flux/model_inference/Nexus-Gen-Editing.py)|[code](./examples/flux/model_inference_low_vram/Nexus-Gen-Editing.py)|[code](./examples/flux/model_training/full/FLUX.1-NexusGen-Edit.sh)|[code](./examples/flux/model_training/validate_full/Nexus-Gen-Editing.py)|[code](./examples/flux/model_training/lora/FLUX.1-NexusGen-Edit.sh)|[code](./examples/flux/model_training/validate_lora/Nexus-Gen-Editing.py)|
+|[Nexus-Gen](https://www.modelscope.cn/models/DiffSynth-Studio/Nexus-GenV2)|`nexus_gen_reference_image`|[code](./examples/flux/model_inference/Nexus-Gen-Editing.py)|[code](./examples/flux/model_inference_low_vram/Nexus-Gen-Editing.py)|[code](./examples/flux/model_training/full/Nexus-Gen.sh)|[code](./examples/flux/model_training/validate_full/Nexus-Gen.py)|[code](./examples/flux/model_training/lora/Nexus-Gen.sh)|[code](./examples/flux/model_training/validate_lora/Nexus-Gen.py)|
+
 </details>
 
 ### Wan 系列

diffsynth/models/nexus_gen.py

@@ -1,18 +1,77 @@
 import torch
 from PIL import Image
-from qwen_vl_utils import smart_resize
-from transformers import AutoConfig
-from .nexus_gen_ar_model import Qwen2_5_VLForConditionalGeneration, Qwen2_5_VLProcessor
 
 
 class NexusGenAutoregressiveModel(torch.nn.Module):
-    def __init__(self, model_path="models/DiffSynth-Studio/Nexus-GenV2", max_length=1024, max_pixels=262640, dtype=torch.bfloat16, device="cuda"):
+    def __init__(self, max_length=1024, max_pixels=262640):
         super(NexusGenAutoregressiveModel, self).__init__()
+        from .nexus_gen_ar_model import Qwen2_5_VLForConditionalGeneration
+        from transformers import Qwen2_5_VLConfig
         self.max_length = max_length
         self.max_pixels = max_pixels
-        model_config = AutoConfig.from_pretrained(model_path)
+        model_config = Qwen2_5_VLConfig(**{
+            "_name_or_path": "DiffSynth-Studio/Nexus-GenV2",
+            "architectures": [
+                "Qwen2_5_VLForConditionalGeneration"
+            ],
+            "attention_dropout": 0.0,
+            "auto_map": {
+                "AutoConfig": "configuration_qwen2_5_vl.Qwen2_5_VLConfig",
+                "AutoModel": "modeling_qwen2_5_vl.Qwen2_5_VLModel",
+                "AutoModelForCausalLM": "modeling_qwen2_5_vl.Qwen2_5_VLForConditionalGeneration"
+            },
+            "bos_token_id": 151643,
+            "eos_token_id": 151645,
+            "hidden_act": "silu",
+            "hidden_size": 3584,
+            "image_token_id": 151655,
+            "initializer_range": 0.02,
+            "intermediate_size": 18944,
+            "max_position_embeddings": 128000,
+            "max_window_layers": 28,
+            "model_type": "qwen2_5_vl",
+            "num_attention_heads": 28,
+            "num_hidden_layers": 28,
+            "num_key_value_heads": 4,
+            "pad_token_id": 151643,
+            "rms_norm_eps": 1e-06,
+            "rope_scaling": {
+                "mrope_section": [
+                16,
+                24,
+                24
+                ],
+                "rope_type": "default",
+                "type": "default"
+            },
+            "rope_theta": 1000000.0,
+            "sliding_window": 32768,
+            "tie_word_embeddings": False,
+            "torch_dtype": "bfloat16",
+            "transformers_version": "4.49.0",
+            "use_cache": False,
+            "use_sliding_window": False,
+            "video_token_id": 151656,
+            "vision_config": {
+                "hidden_size": 1280,
+                "in_chans": 3,
+                "model_type": "qwen2_5_vl",
+                "spatial_patch_size": 14,
+                "tokens_per_second": 2,
+                "torch_dtype": "bfloat16"
+            },
+            "vision_end_token_id": 151653,
+            "vision_start_token_id": 151652,
+            "vision_token_id": 151654,
+            "vocab_size": 152064
+        })
         self.model = Qwen2_5_VLForConditionalGeneration(model_config)
-        self.processor = Qwen2_5_VLProcessor.from_pretrained(model_path)
+        self.processor = None
+        
+        
+    def load_processor(self, path):
+        from .nexus_gen_ar_model import Qwen2_5_VLProcessor
+        self.processor = Qwen2_5_VLProcessor.from_pretrained(path)
 
 
     @staticmethod
@@ -20,6 +79,7 @@ class NexusGenAutoregressiveModel(torch.nn.Module):
         return NexusGenAutoregressiveModelStateDictConverter()
 
     def bound_image(self, image, max_pixels=262640):
+        from qwen_vl_utils import smart_resize
         resized_height, resized_width = smart_resize(
             image.height,
             image.width,

diffsynth/models/nexus_gen_projector.py

@@ -2,9 +2,8 @@ import math
 import torch
 import torch.nn as nn
 from typing import Optional, Tuple
-from transformers.activations import ACT2FN
+
-from transformers.modeling_rope_utils import _compute_default_rope_parameters
+
-from transformers import AutoConfig
 
 def rotate_half(x):
     """Rotates half the hidden dims of the input."""
@@ -39,6 +38,7 @@ class Qwen2_5_VLRotaryEmbedding(nn.Module):
         self.original_max_seq_len = config.max_position_embeddings
 
         self.config = config
+        from transformers.modeling_rope_utils import _compute_default_rope_parameters
         self.rope_init_fn = _compute_default_rope_parameters
 
         inv_freq, self.attention_scaling = self.rope_init_fn(self.config, device)
@@ -181,6 +181,7 @@ class Qwen2_5_VLAttention(nn.Module):
 class Qwen2MLP(nn.Module):
     def __init__(self, config):
         super().__init__()
+        from transformers.activations import ACT2FN
         self.config = config
         self.hidden_size = config.hidden_size
         self.intermediate_size = config.intermediate_size
@@ -254,6 +255,8 @@ class Qwen2_5_VLDecoderLayer(nn.Module):
 class NexusGenImageEmbeddingMerger(nn.Module):
     def __init__(self, model_path="models/DiffSynth-Studio/Nexus-GenV2", num_layers=1, out_channel=4096, expand_ratio=4, device='cpu'):
         super().__init__()
+        from transformers import AutoConfig
+        from transformers.activations import ACT2FN
         config = AutoConfig.from_pretrained(model_path)
         self.config = config
         self.num_layers = num_layers

diffsynth/pipelines/flux_image_new.py

@@ -375,6 +375,7 @@ class FluxImagePipeline(BasePipeline):
         torch_dtype: torch.dtype = torch.bfloat16,
         device: Union[str, torch.device] = "cuda",
         model_configs: list[ModelConfig] = [],
+        nexus_gen_processor_config: ModelConfig = None,
     ):
         # Download and load models
         model_manager = ModelManager()
@@ -406,6 +407,9 @@ class FluxImagePipeline(BasePipeline):
         pipe.nexus_gen = model_manager.fetch_model("nexus_gen_llm")
         pipe.nexus_gen_generation_adapter = model_manager.fetch_model("nexus_gen_generation_adapter")
         pipe.nexus_gen_editing_adapter = model_manager.fetch_model("nexus_gen_editing_adapter")
+        if nexus_gen_processor_config is not None and pipe.nexus_gen is not None:
+            nexus_gen_processor_config.download_if_necessary()
+            pipe.nexus_gen.load_processor(nexus_gen_processor_config.path)
         
         # ControlNet
         controlnets = []

examples/flux/README.md

@@ -50,11 +50,12 @@ image.save("image.jpg")
 |[FLUX.1-dev-Controlnet-Upscaler](https://www.modelscope.cn/models/jasperai/Flux.1-dev-Controlnet-Upscaler)|`controlnet_inputs`|[code](./model_inference/FLUX.1-dev-Controlnet-Upscaler.py)|[code](./model_inference_low_vram/FLUX.1-dev-Controlnet-Upscaler.py)|[code](./model_training/full/FLUX.1-dev-Controlnet-Upscaler.sh)|[code](./model_training/validate_full/FLUX.1-dev-Controlnet-Upscaler.py)|[code](./model_training/lora/FLUX.1-dev-Controlnet-Upscaler.sh)|[code](./model_training/validate_lora/FLUX.1-dev-Controlnet-Upscaler.py)|
 |[FLUX.1-dev-IP-Adapter](https://www.modelscope.cn/models/InstantX/FLUX.1-dev-IP-Adapter)|`ipadapter_images`, `ipadapter_scale`|[code](./model_inference/FLUX.1-dev-IP-Adapter.py)|[code](./model_inference_low_vram/FLUX.1-dev-IP-Adapter.py)|[code](./model_training/full/FLUX.1-dev-IP-Adapter.sh)|[code](./model_training/validate_full/FLUX.1-dev-IP-Adapter.py)|[code](./model_training/lora/FLUX.1-dev-IP-Adapter.sh)|[code](./model_training/validate_lora/FLUX.1-dev-IP-Adapter.py)|
 |[FLUX.1-dev-InfiniteYou](https://www.modelscope.cn/models/ByteDance/InfiniteYou)|`infinityou_id_image`, `infinityou_guidance`, `controlnet_inputs`|[code](./model_inference/FLUX.1-dev-InfiniteYou.py)|[code](./model_inference_low_vram/FLUX.1-dev-InfiniteYou.py)|[code](./model_training/full/FLUX.1-dev-InfiniteYou.sh)|[code](./model_training/validate_full/FLUX.1-dev-InfiniteYou.py)|[code](./model_training/lora/FLUX.1-dev-InfiniteYou.sh)|[code](./model_training/validate_lora/FLUX.1-dev-InfiniteYou.py)|
-|[FLUX.1-dev-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Eligen)|`eligen_entity_prompts`, `eligen_entity_masks`, `eligen_enable_on_negative`, `eligen_enable_inpaint`|[code](./model_inference/FLUX.1-dev-EliGen.py)|[code](./model_inference_low_vram/FLUX.1-dev-EliGen.py)|-|-|||
+|[FLUX.1-dev-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Eligen)|`eligen_entity_prompts`, `eligen_entity_masks`, `eligen_enable_on_negative`, `eligen_enable_inpaint`|[code](./model_inference/FLUX.1-dev-EliGen.py)|[code](./model_inference_low_vram/FLUX.1-dev-EliGen.py)|-|-|[code](./model_training/lora/FLUX.1-dev-EliGen.sh)|[code](./model_training/validate_lora/FLUX.1-dev-EliGen.py)|
 |[FLUX.1-dev-LoRA-Encoder](https://www.modelscope.cn/models/DiffSynth-Studio/LoRA-Encoder-FLUX.1-Dev)|`lora_encoder_inputs`, `lora_encoder_scale`|[code](./model_inference/FLUX.1-dev-LoRA-Encoder.py)|[code](./model_inference_low_vram/FLUX.1-dev-LoRA-Encoder.py)|[code](./model_training/full/FLUX.1-dev-LoRA-Encoder.sh)|[code](./model_training/validate_full/FLUX.1-dev-LoRA-Encoder.py)|-|-|
 |[FLUX.1-dev-LoRA-Fusion-Preview](https://modelscope.cn/models/DiffSynth-Studio/LoRAFusion-preview-FLUX.1-dev)||[code](./model_inference/FLUX.1-dev-LoRA-Fusion.py)|-|-|-|-|-|
 |[Step1X-Edit](https://www.modelscope.cn/models/stepfun-ai/Step1X-Edit)|`step1x_reference_image`|[code](./model_inference/Step1X-Edit.py)|[code](./model_inference_low_vram/Step1X-Edit.py)|[code](./model_training/full/Step1X-Edit.sh)|[code](./model_training/validate_full/Step1X-Edit.py)|[code](./model_training/lora/Step1X-Edit.sh)|[code](./model_training/validate_lora/Step1X-Edit.py)|
 |[FLEX.2-preview](https://www.modelscope.cn/models/ostris/Flex.2-preview)|`flex_inpaint_image`, `flex_inpaint_mask`, `flex_control_image`, `flex_control_strength`, `flex_control_stop`|[code](./model_inference/FLEX.2-preview.py)|[code](./model_inference_low_vram/FLEX.2-preview.py)|[code](./model_training/full/FLEX.2-preview.sh)|[code](./model_training/validate_full/FLEX.2-preview.py)|[code](./model_training/lora/FLEX.2-preview.sh)|[code](./model_training/validate_lora/FLEX.2-preview.py)|
+|[Nexus-Gen](https://www.modelscope.cn/models/DiffSynth-Studio/Nexus-GenV2)|`nexus_gen_reference_image`|[code](./model_inference/Nexus-Gen-Editing.py)|[code](./model_inference_low_vram/Nexus-Gen-Editing.py)|[code](./model_training/full/Nexus-Gen.sh)|[code](./model_training/validate_full/Nexus-Gen.py)|[code](./model_training/lora/Nexus-Gen.sh)|[code](./model_training/validate_lora/Nexus-Gen.py)|
 
 ## Model Inference
 

examples/flux/README_zh.md

@@ -50,11 +50,12 @@ image.save("image.jpg")
 |[FLUX.1-dev-Controlnet-Upscaler](https://www.modelscope.cn/models/jasperai/Flux.1-dev-Controlnet-Upscaler)|`controlnet_inputs`|[code](./model_inference/FLUX.1-dev-Controlnet-Upscaler.py)|[code](./model_inference_low_vram/FLUX.1-dev-Controlnet-Upscaler.py)|[code](./model_training/full/FLUX.1-dev-Controlnet-Upscaler.sh)|[code](./model_training/validate_full/FLUX.1-dev-Controlnet-Upscaler.py)|[code](./model_training/lora/FLUX.1-dev-Controlnet-Upscaler.sh)|[code](./model_training/validate_lora/FLUX.1-dev-Controlnet-Upscaler.py)|
 |[FLUX.1-dev-IP-Adapter](https://www.modelscope.cn/models/InstantX/FLUX.1-dev-IP-Adapter)|`ipadapter_images`, `ipadapter_scale`|[code](./model_inference/FLUX.1-dev-IP-Adapter.py)|[code](./model_inference_low_vram/FLUX.1-dev-IP-Adapter.py)|[code](./model_training/full/FLUX.1-dev-IP-Adapter.sh)|[code](./model_training/validate_full/FLUX.1-dev-IP-Adapter.py)|[code](./model_training/lora/FLUX.1-dev-IP-Adapter.sh)|[code](./model_training/validate_lora/FLUX.1-dev-IP-Adapter.py)|
 |[FLUX.1-dev-InfiniteYou](https://www.modelscope.cn/models/ByteDance/InfiniteYou)|`infinityou_id_image`, `infinityou_guidance`, `controlnet_inputs`|[code](./model_inference/FLUX.1-dev-InfiniteYou.py)|[code](./model_inference_low_vram/FLUX.1-dev-InfiniteYou.py)|[code](./model_training/full/FLUX.1-dev-InfiniteYou.sh)|[code](./model_training/validate_full/FLUX.1-dev-InfiniteYou.py)|[code](./model_training/lora/FLUX.1-dev-InfiniteYou.sh)|[code](./model_training/validate_lora/FLUX.1-dev-InfiniteYou.py)|
-|[FLUX.1-dev-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Eligen)|`eligen_entity_prompts`, `eligen_entity_masks`, `eligen_enable_on_negative`, `eligen_enable_inpaint`|[code](./model_inference/FLUX.1-dev-EliGen.py)|[code](./model_inference_low_vram/FLUX.1-dev-EliGen.py)|-|-|||
+|[FLUX.1-dev-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Eligen)|`eligen_entity_prompts`, `eligen_entity_masks`, `eligen_enable_on_negative`, `eligen_enable_inpaint`|[code](./model_inference/FLUX.1-dev-EliGen.py)|[code](./model_inference_low_vram/FLUX.1-dev-EliGen.py)|-|-|[code](./model_training/lora/FLUX.1-dev-EliGen.sh)|[code](./model_training/validate_lora/FLUX.1-dev-EliGen.py)|
 |[FLUX.1-dev-LoRA-Encoder](https://www.modelscope.cn/models/DiffSynth-Studio/LoRA-Encoder-FLUX.1-Dev)|`lora_encoder_inputs`, `lora_encoder_scale`|[code](./model_inference/FLUX.1-dev-LoRA-Encoder.py)|[code](./model_inference_low_vram/FLUX.1-dev-LoRA-Encoder.py)|[code](./model_training/full/FLUX.1-dev-LoRA-Encoder.sh)|[code](./model_training/validate_full/FLUX.1-dev-LoRA-Encoder.py)|-|-|
 |[FLUX.1-dev-LoRA-Fusion-Preview](https://modelscope.cn/models/DiffSynth-Studio/LoRAFusion-preview-FLUX.1-dev)||[code](./model_inference/FLUX.1-dev-LoRA-Fusion.py)|-|-|-|-|-|
 |[Step1X-Edit](https://www.modelscope.cn/models/stepfun-ai/Step1X-Edit)|`step1x_reference_image`|[code](./model_inference/Step1X-Edit.py)|[code](./model_inference_low_vram/Step1X-Edit.py)|[code](./model_training/full/Step1X-Edit.sh)|[code](./model_training/validate_full/Step1X-Edit.py)|[code](./model_training/lora/Step1X-Edit.sh)|[code](./model_training/validate_lora/Step1X-Edit.py)|
 |[FLEX.2-preview](https://www.modelscope.cn/models/ostris/Flex.2-preview)|`flex_inpaint_image`, `flex_inpaint_mask`, `flex_control_image`, `flex_control_strength`, `flex_control_stop`|[code](./model_inference/FLEX.2-preview.py)|[code](./model_inference_low_vram/FLEX.2-preview.py)|[code](./model_training/full/FLEX.2-preview.sh)|[code](./model_training/validate_full/FLEX.2-preview.py)|[code](./model_training/lora/FLEX.2-preview.sh)|[code](./model_training/validate_lora/FLEX.2-preview.py)|
+|[Nexus-Gen](https://www.modelscope.cn/models/DiffSynth-Studio/Nexus-GenV2)|`nexus_gen_reference_image`|[code](./model_inference/Nexus-Gen-Editing.py)|[code](./model_inference_low_vram/Nexus-Gen-Editing.py)|[code](./model_training/full/Nexus-Gen.sh)|[code](./model_training/validate_full/Nexus-Gen.py)|[code](./model_training/lora/Nexus-Gen.sh)|[code](./model_training/validate_lora/Nexus-Gen.py)|
 
 ## 模型推理
 

examples/flux/model_inference/Nexus-Gen-Editing.py

@@ -2,7 +2,8 @@ import importlib
 import torch
 from PIL import Image
 from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
-from modelscope import snapshot_download, dataset_snapshot_download
+from modelscope import dataset_snapshot_download
+
 
 if importlib.util.find_spec("transformers") is None:
     raise ImportError("You are using Nexus-GenV2. It depends on transformers, which is not installed. Please install it with `pip install transformers==4.49.0`.")
@@ -10,7 +11,7 @@ else:
     import transformers
     assert transformers.__version__ == "4.49.0", "Nexus-GenV2 requires transformers==4.49.0, please install it with `pip install transformers==4.49.0`."
 
-snapshot_download("DiffSynth-Studio/Nexus-GenV2", local_dir="models/DiffSynth-Studio/Nexus-GenV2")
+
 pipe = FluxImagePipeline.from_pretrained(
     torch_dtype=torch.bfloat16,
     device="cuda",
@@ -21,6 +22,7 @@ pipe = FluxImagePipeline.from_pretrained(
         ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
         ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
     ],
+    nexus_gen_processor_config=ModelConfig("DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="processor"),
 )
 
 dataset_snapshot_download(dataset_id="DiffSynth-Studio/examples_in_diffsynth", local_dir="./", allow_file_pattern=f"data/examples/nexusgen/cat.jpg")

examples/flux/model_inference/Nexus-Gen-Generation.py

@@ -1,7 +1,7 @@
 import importlib
 import torch
 from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
-from modelscope import snapshot_download
+
 
 if importlib.util.find_spec("transformers") is None:
     raise ImportError("You are using Nexus-GenV2. It depends on transformers, which is not installed. Please install it with `pip install transformers==4.49.0`.")
@@ -9,7 +9,7 @@ else:
     import transformers
     assert transformers.__version__ == "4.49.0", "Nexus-GenV2 requires transformers==4.49.0, please install it with `pip install transformers==4.49.0`."
 
-snapshot_download("DiffSynth-Studio/Nexus-GenV2", local_dir="models/DiffSynth-Studio/Nexus-GenV2")
+
 pipe = FluxImagePipeline.from_pretrained(
     torch_dtype=torch.bfloat16,
     device="cuda",
@@ -20,6 +20,7 @@ pipe = FluxImagePipeline.from_pretrained(
         ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
         ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
     ],
+    nexus_gen_processor_config=ModelConfig("DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="processor"),
 )
 
 prompt = "一只可爱的猫咪"

examples/flux/model_inference_low_vram/Nexus-Gen-Generation.py

@@ -0,0 +1,32 @@
+import importlib
+import torch
+from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
+from modelscope import snapshot_download
+
+if importlib.util.find_spec("transformers") is None:
+    raise ImportError("You are using Nexus-GenV2. It depends on transformers, which is not installed. Please install it with `pip install transformers==4.49.0`.")
+else:
+    import transformers
+    assert transformers.__version__ == "4.49.0", "Nexus-GenV2 requires transformers==4.49.0, please install it with `pip install transformers==4.49.0`."
+
+snapshot_download("DiffSynth-Studio/Nexus-GenV2", local_dir="models/DiffSynth-Studio/Nexus-GenV2")
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="model*.safetensors"),
+        ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="generation_decoder.bin"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+    ],
+)
+pipe.enable_vram_management()
+
+prompt = "一只可爱的猫咪"
+image = pipe(
+    prompt=prompt, negative_prompt="",
+    seed=0, cfg_scale=3, num_inference_steps=50,
+    height=1024, width=1024,
+)
+image.save("cat.jpg")