diff --git a/README.md b/README.md
index 93aa836..d2e81be 100644
--- a/README.md
+++ b/README.md
@@ -760,6 +760,37 @@ Example code for Wan is available at: [/examples/wanvideo/](/examples/wanvideo/)
DiffSynth-Studio is not just an engineered model framework, but also an incubator for innovative achievements.
+
+
+Spectral Evolution Search: Efficient Inference-Time Scaling for Reward-Aligned Image Generation
+
+- Paper: [Spectral Evolution Search: Efficient Inference-Time Scaling for Reward-Aligned Image Generation
+](https://arxiv.org/abs/2602.03208)
+- Sample Code: []()
+
+|FLUX|FLUX + SES|Qwen-Image|Qwen-Image + SES|
+|-|-|-|-|
+|||||
+
+
+
+
+
+
+VIRAL: Visual In-Context Reasoning via Analogy in Diffusion Transformers
+
+- Paper: [VIRAL: Visual In-Context Reasoning via Analogy in Diffusion Transformers
+](https://arxiv.org/abs/2602.03210)
+- Sample code: [/examples/flux/model_inference/FLUX.1-dev-LoRA-Fusion.py](/examples/flux/model_inference/FLUX.1-dev-LoRA-Fusion.py)
+- Model: [ModelScope](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-2511-ICEdit-LoRA)
+
+|Example 1|Example 2|Query|Output|
+|-|-|-|-|
+|||||
+
+
+
+
AttriCtrl: Attribute Intensity Control for Image Generation Models
@@ -770,7 +801,7 @@ DiffSynth-Studio is not just an engineered model framework, but also an incubato
|brightness scale = 0.1|brightness scale = 0.3|brightness scale = 0.5|brightness scale = 0.7|brightness scale = 0.9|
|-|-|-|-|-|
-||||||
+||||||
@@ -785,10 +816,10 @@ DiffSynth-Studio is not just an engineered model framework, but also an incubato
||[LoRA 1](https://modelscope.cn/models/cancel13/cxsk)|[LoRA 2](https://modelscope.cn/models/wy413928499/xuancai2)|[LoRA 3](https://modelscope.cn/models/DiffSynth-Studio/ArtAug-lora-FLUX.1dev-v1)|[LoRA 4](https://modelscope.cn/models/hongyanbujian/JPL)|
|-|-|-|-|-|
-|[LoRA 1](https://modelscope.cn/models/cancel13/cxsk) |||||
-|[LoRA 2](https://modelscope.cn/models/wy413928499/xuancai2) |||||
-|[LoRA 3](https://modelscope.cn/models/DiffSynth-Studio/ArtAug-lora-FLUX.1dev-v1) |||||
-|[LoRA 4](https://modelscope.cn/models/hongyanbujian/JPL) |||||
+|[LoRA 1](https://modelscope.cn/models/cancel13/cxsk) |||||
+|[LoRA 2](https://modelscope.cn/models/wy413928499/xuancai2) |||||
+|[LoRA 3](https://modelscope.cn/models/DiffSynth-Studio/ArtAug-lora-FLUX.1dev-v1) |||||
+|[LoRA 4](https://modelscope.cn/models/hongyanbujian/JPL) |||||
diff --git a/README_zh.md b/README_zh.md
index 2aee367..d361eff 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -762,6 +762,35 @@ DiffSynth-Studio 不仅仅是一个工程化的模型框架，更是创新成果
+Spectral Evolution Search: 用于奖励对齐图像生成的高效推理阶段缩放
+
+- 论文：[Spectral Evolution Search: Efficient Inference-Time Scaling for Reward-Aligned Image Generation
+](https://arxiv.org/abs/2602.03208)
+- 代码样例：[]()
+
+|FLUX|FLUX + SES|Qwen-Image|Qwen-Image + SES|
+|-|-|-|-|
+|||||
+
+
+
+
+
+VIRAL：基于DiT模型的类比视觉上下文推理
+
+- 论文：[VIRAL: Visual In-Context Reasoning via Analogy in Diffusion Transformers
+](https://arxiv.org/abs/2602.03210)
+- 代码样例：[/examples/qwen_image/model_inference/Qwen-Image-Edit-2511-ICEdit.py](/examples/qwen_image/model_inference/Qwen-Image-Edit-2511-ICEdit.py)
+- 模型：[ModelScope](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-2511-ICEdit-LoRA)
+
+|Example 1|Example 2|Query|Output|
+|-|-|-|-|
+|||||
+
+
+
+
+
AttriCtrl: 图像生成模型的属性强度控制
- 论文：[AttriCtrl: Fine-Grained Control of Aesthetic Attribute Intensity in Diffusion Models
@@ -771,7 +800,7 @@ DiffSynth-Studio 不仅仅是一个工程化的模型框架，更是创新成果
|brightness scale = 0.1|brightness scale = 0.3|brightness scale = 0.5|brightness scale = 0.7|brightness scale = 0.9|
|-|-|-|-|-|
-||||||
+||||||
@@ -787,10 +816,10 @@ DiffSynth-Studio 不仅仅是一个工程化的模型框架，更是创新成果
||[LoRA 1](https://modelscope.cn/models/cancel13/cxsk)|[LoRA 2](https://modelscope.cn/models/wy413928499/xuancai2)|[LoRA 3](https://modelscope.cn/models/DiffSynth-Studio/ArtAug-lora-FLUX.1dev-v1)|[LoRA 4](https://modelscope.cn/models/hongyanbujian/JPL)|
|-|-|-|-|-|
-|[LoRA 1](https://modelscope.cn/models/cancel13/cxsk) |||||
-|[LoRA 2](https://modelscope.cn/models/wy413928499/xuancai2) |||||
-|[LoRA 3](https://modelscope.cn/models/DiffSynth-Studio/ArtAug-lora-FLUX.1dev-v1) |||||
-|[LoRA 4](https://modelscope.cn/models/hongyanbujian/JPL) |||||
+|[LoRA 1](https://modelscope.cn/models/cancel13/cxsk) |||||
+|[LoRA 2](https://modelscope.cn/models/wy413928499/xuancai2) |||||
+|[LoRA 3](https://modelscope.cn/models/DiffSynth-Studio/ArtAug-lora-FLUX.1dev-v1) |||||
+|[LoRA 4](https://modelscope.cn/models/hongyanbujian/JPL) |||||
diff --git a/examples/qwen_image/model_inference/Qwen-Image-Edit-2511-ICEdit.py b/examples/qwen_image/model_inference/Qwen-Image-Edit-2511-ICEdit.py
new file mode 100644
index 0000000..67eca5a
--- /dev/null
+++ b/examples/qwen_image/model_inference/Qwen-Image-Edit-2511-ICEdit.py
@@ -0,0 +1,47 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+from modelscope import snapshot_download
+from PIL import Image
+import torch
+
+# Load models
+pipe = QwenImagePipeline.from_pretrained(
+ torch_dtype=torch.bfloat16,
+ device="cuda",
+ model_configs=[
+ ModelConfig(model_id="Qwen/Qwen-Image-Edit-2511", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
+ ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
+ ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+ ],
+ processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"),
+)
+lora = ModelConfig(
+ model_id="DiffSynth-Studio/Qwen-Image-Edit-2511-ICEdit-LoRA",
+ origin_file_pattern="model.safetensors"
+)
+pipe.load_lora(pipe.dit, lora)
+
+# Load images
+snapshot_download(
+ "DiffSynth-Studio/Qwen-Image-Edit-2511-ICEdit-LoRA",
+ local_dir="./data",
+ allow_file_pattern="assets/*"
+)
+edit_image = [
+ Image.open("data/assets/image1_original.png"),
+ Image.open("data/assets/image1_edit_1.png"),
+ Image.open("data/assets/image2_original.png")
+]
+prompt = "Edit image 3 based on the transformation from image 1 to image 2."
+negative_prompt = "泛黄，AI感，不真实，丑陋，油腻的皮肤，异常的肢体，不协调的肢体"
+
+# Generate
+image_4 = pipe(
+ prompt=prompt, negative_prompt=negative_prompt,
+ edit_image=edit_image,
+ seed=1,
+ num_inference_steps=50,
+ height=1280,
+ width=720,
+ zero_cond_t=True,
+)
+image_4.save("image.png")
\ No newline at end of file
diff --git a/examples/wanvideo/model_training/full/Wan2.2-S2V-14B.sh b/examples/wanvideo/model_training/full/Wan2.2-S2V-14B.sh
index 10c4a5a..9eec871 100644
--- a/examples/wanvideo/model_training/full/Wan2.2-S2V-14B.sh
+++ b/examples/wanvideo/model_training/full/Wan2.2-S2V-14B.sh
@@ -7,6 +7,7 @@ accelerate launch --config_file examples/wanvideo/model_training/full/accelerate
--num_frames 81 \
--dataset_repeat 100 \
--model_id_with_origin_paths "Wan-AI/Wan2.2-S2V-14B:diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.2-S2V-14B:wav2vec2-large-xlsr-53-english/model.safetensors,Wan-AI/Wan2.2-S2V-14B:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.2-S2V-14B:Wan2.1_VAE.pth" \
+ --audio_processor_path "Wan-AI/Wan2.2-S2V-14B:wav2vec2-large-xlsr-53-english/" \
--learning_rate 1e-5 \
--num_epochs 1 \
--trainable_models "dit" \
diff --git a/examples/wanvideo/model_training/lora/Wan2.2-S2V-14B.sh b/examples/wanvideo/model_training/lora/Wan2.2-S2V-14B.sh
index 510796b..ec5bb87 100644
--- a/examples/wanvideo/model_training/lora/Wan2.2-S2V-14B.sh
+++ b/examples/wanvideo/model_training/lora/Wan2.2-S2V-14B.sh
@@ -7,6 +7,7 @@ accelerate launch --config_file examples/wanvideo/model_training/full/accelerate
--num_frames 81 \
--dataset_repeat 100 \
--model_id_with_origin_paths "Wan-AI/Wan2.2-S2V-14B:diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.2-S2V-14B:wav2vec2-large-xlsr-53-english/model.safetensors,Wan-AI/Wan2.2-S2V-14B:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.2-S2V-14B:Wan2.1_VAE.pth" \
+ --audio_processor_path "Wan-AI/Wan2.2-S2V-14B:wav2vec2-large-xlsr-53-english/" \
--learning_rate 1e-4 \
--num_epochs 5 \
--remove_prefix_in_ckpt "pipe.dit." \
diff --git a/examples/wanvideo/model_training/train.py b/examples/wanvideo/model_training/train.py
index 4973438..d4074a6 100644
--- a/examples/wanvideo/model_training/train.py
+++ b/examples/wanvideo/model_training/train.py
@@ -33,7 +33,7 @@ class WanTrainingModule(DiffusionTrainingModule):
# Load models
model_configs = self.parse_model_configs(model_paths, model_id_with_origin_paths, fp8_models=fp8_models, offload_models=offload_models, device=device)
tokenizer_config = ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="google/umt5-xxl/") if tokenizer_path is None else ModelConfig(tokenizer_path)
- audio_processor_config = ModelConfig(model_id="Wan-AI/Wan2.2-S2V-14B", origin_file_pattern="wav2vec2-large-xlsr-53-english/") if audio_processor_path is None else ModelConfig(audio_processor_path)
+ audio_processor_config = self.parse_path_or_model_id(audio_processor_path)
self.pipe = WanVideoPipeline.from_pretrained(torch_dtype=torch.bfloat16, device=device, model_configs=model_configs, tokenizer_config=tokenizer_config, audio_processor_config=audio_processor_config)
self.pipe = self.split_pipeline_units(task, self.pipe, trainable_models, lora_base_model)