用感觉来理解未知的事物，这疑似有点太原始了，但是你有更好的方法吗。Understanding the unknown through sensation, this method may be somewhat primitive, but do you have a better approach.<hr />一次完整的模型处理需要13个流程，这些流程分为3种，总之我会尽量完整的解释给你们A complete model processing requires 13 processes, which are divided into 3 types. In short, I will try my best to explain it to you thoroughly流程1拆解模型 A ：(被提取模型) 模型 B ：Extract component B 模型 C : Extract component Cα= -1Process 1 BreakdownModel a：( extracted model ) Model b ：Extract component B Model c : Extract component Cα= -1流程2阶段提取模型 A ：流程1提取物 1 模型 B ：(被提取模型) 模型 模型 C ：流程1提取物 1α= 2进行这一步混合后会得到 流程1提取物2，之后你需要不断更换模型A和模型C 用于得到 流程1提取物4Phase 2 extractionModel A: Process 1 Extract 1 Model B: (Extracted Model) Model C: Process 1 Extract 1α = 2After this step of mixing, you will obtain Process 1 Extract 2. Then, you need to continuously switch between Model A and Model C to obtain Process 1 Extract 4我简单介绍一下获取的模型类型Let me briefly introduce the types of models obtained流程1提取物 1：通过提取模型以及混合算法，去除了被提取模型的基础部分，而留下来的则是这个模型的画风。这部分我称作画风1.0Process 1 Extract 1：By extracting the model and using a mixed algorithm, the foundational parts of the extracted model have been removed, leaving behind what I refer to as the style of the model. This part I call Style 1.0流程1提取物 2：基础1.0 、流程1提取物 3：画风2.0 、流程1提取物 4：基础2.0Process 1 Extract 2：Basic 1.0 Process 1 Extract 3：Style 2.0 Process 1 Extract 4：Basic 2.0流程3提纯 流程3需要结合之前的流程使用模型 A ：画风2.0 模型 B ：画风2.0拆解 流程1提取物 3 模型 C ：画风2.0α = -1现在这个模型就回到了未拆解的阶段，并成功的进行了活性化基础2.0的混合路线也是如此Phase 3 refine Process 3 needs to be used in conjunction with the previous processesModel A ：Style 2.0 模型 B ：Style 2.0 Breakdown Process 1 Extract 3 模型 C ：Style 2.0α = -1The model has now returned to the unassembled stage and has successfully been ActivationThe mixed route of Basic 2.0 is the same.这种方式也可以增加提取物信息的深度，不过需要进行一些调整This method can also enhance the depth of the extract information, but some adjustments are needed我承认我并不是一个专业的研究者，我所做的一切或许毫无意义，又或者我发现的都是错误的，总之，我现在已经感到了疲劳，显然我已经失去了热情。我把大量的时间用在模型混合上，但始终没有得到突破式的发展，或许从最开始我的方向便是错误的。模型训练是AI的正确路线，模型混合不是。模型版本升级是正确路线，模型混合不是。所以你有什么想法吗。

KM_Model_splicing_material_demonstration

关于这个模型使用:<a target="_blank" rel="ugc" href="https://civitai.com/models/274949?modelVersionId=645426">https://civitai.com/models/274949?modelVersionId=645426</a> , 和 <a target="_blank" rel="ugc" href="https://civitai.com/models/16828">https://civitai.com/models/16828</a> 我尝试混合两个模型的特征，或许单独展示会更好，但那样并不有趣。虽然这个模型只有在特定的情况下才可以很好的表现两个模型的特点。但是我想这应该能展示我的成果。Regarding the use of this model:<a target="_blank" rel="ugc" href="https://civitai.com/models/274949?modelVersionId=645426">https://civitai.com/models/274949?modelVersionId=645426</a>, and <a target="_blank" rel="ugc" href="https://civitai.com/models/16828">https://civitai.com/models/16828</a> I attempted to blend the features of the two models, perhaps showcasing them separately would be better, but that would not be interesting. Although this model only performs well under specific circumstances, I believe it should be able to demonstrate my results完善了提取流程，现在更加规范而且不需要调整数值。Improved the extraction process, now more standardized and does not require adjustment of values尝试提取和纯化模型特征，但不确定其是否具有普遍性Attempt to extract and purify model characteristics, but uncertain if it is universal好了，等模型素材下载人数足够多我就会上传我的用于提取的模型，以及公布规范化的的流程。Once the number of downloads for the model materials is sufficient, I will upload my model for extraction and publish the standardized process现在推广实在还是过早，我怀疑并没有多少人做着和我一样的事情It is indeed too early to promote now, and I suspect that I am the only one engaging in such meaningless activities at this moment{ "sd_merge_models": { "803e80a9ca00917dbbcdd411190f17b0a8c84e2cb2588cf0e1b35b58e4a6cef1": { "name": "高浓度_基准浓度画风_8-6 模型解析Xa80sb 1.1.fp16", "legacy_hash": "04c9ef50" }, "659298f1de33fdf187fd207e4e3956cbf1d68c062a78630f5eb8be48b866769e": { "name": "8-6 模型拆解4-24画片测试14X3.fp16", "legacy_hash": "2f67c56a" } }, "format": "pt", "sd_merge_recipe": { "type": "sd-webui-supermerger", "weights_alpha": null, "weights_beta": null, "weights_alpha_orig": null, "weights_beta_orig": null, "model_a": "803e80a9ca00917dbbcdd411190f17b0a8c84e2cb2588cf0e1b35b58e4a6cef1", "model_b": "659298f1de33fdf187fd207e4e3956cbf1d68c062a78630f5eb8be48b866769e", "model_c": "803e80a9ca00917dbbcdd411190f17b0a8c84e2cb2588cf0e1b35b58e4a6cef1", "base_alpha": 0.55, "base_beta": 0.611, "mode": "Add difference", "mbw": false, "elemental_merge": "", "calcmode": "trainDifference", "Off": [ "" ] } }

Files with SHA256: 5e7f2ea7624e190174a14737bdd2d5590925155e070ba83c18a27e323c4952fe