EndoCoT：扩散模型中的内生思维链推理扩展

git clone https://github.com/InternLM/EndoCoT
cd EndoCoT
conda create -n EndoCoT python=3.10
conda activate EndoCot
# Please install the version of torch compatible with your machine.
pip install -r requirements.txt
# Please install the version of vLLM compatible with your machine.

def encode_prompt_edit(self, pipe: QwenImagePipeline, prompt, edit_image, is_final, gt_prompt=None, idx=None):

        drop_idx = 64
        if type(prompt[0])==str:
            template =  "<|im_start|>system
Describe the key features of the input image (color, shape, size, texture, objects, background), then explain how the user's text instruction should alter or modify the image. Generate a new image that meets the user's requirements while maintaining consistency with the original input where appropriate.<|im_end|>
<|im_start|>user
<|vision_start|><|image_pad|><|vision_end|>{}<|im_end|>
<|im_start|>assistant
"
            txt = template.format(prompt[0])
            model_inputs = pipe.processor(text=txt, images=edit_image, padding=True, return_tensors="pt").to(pipe.device)
            embedding_layers = pipe.text_encoder.model.language_model.get_input_embeddings()
            with torch.no_grad():
                inputs_embeds = embedding_layers(model_inputs.input_ids)
            self.attention_mask = model_inputs.attention_mask
            self.pixel_values = model_inputs.pixel_values
            self.image_grid_thw = model_inputs.image_grid_thw
        else:
            inputs_embeds= prompt[0]
            
        # dxl: test use
        if is_final==None or idx!=None:
            print("现在在inference。或者stage2训练")
            if idx!=None:
                iter_times = idx-2
            else:
                # infer step
                iter_times = 50
                
            with torch.no_grad():
                inputs_embeds = self.manual_generate_eval(
                    pipe, 
                    inputs_embeds=inputs_embeds,
                    max_new_tokens=iter_times,
                ).detach()
            
            # dxl: only update the last 2 tokens
            if idx!=None:
                inputs_embeds = self.manual_generate_eval(
                    pipe,
                    inputs_embeds=inputs_embeds,
                    max_new_tokens=2,
                )

            generated_embeds = inputs_embeds

		... ... 
        
        # dxl：training
        if is_final!=None and idx==None:
            try:
                generated_embeds, _ = self.manual_generate(
                    pipe,
                    inputs_embeds=inputs_embeds,
                    is_final=is_final,
                    # training steps
                    max_new_tokens=2,
                )
            except Exception as e:
                print(f"Error!: {type(e).__name__} - {e}")
                print(inputs_embeds.shape)
                assert False

        try: 
            return split_hidden_states, generated_embeds, eos_loss
        except:
            print(f"[WARNING] Prompt was not updated correctly for inference.")
            return split_hidden_states

@article{dai2026endocot,
  title={EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models},
  author={Dai, Xuanlang and Zhou, Yujie and Xing, Long and Bu, Jiazi and Wei, Xilin and Liu, Yuhong and Zhang, Beichen and Chen, Kai and Zang, Yuhang},
  journal={arXiv preprint arXiv:2603.12252},
  year={2026}
}