以下是为您整理的相关内容：
关于 FLUX 模型的安装部署：
关于训练 Midjourney 的 prompt：
关于 ComfyUI 图片提示词反推提示词生成：
FLUX.1[dev]FLUX.1[dev fp8]FLUX.1[schnell],选一个.建议选择dev版本的,显卡可以的用fp16,显卡不够用的选fp8.模型下载后,放入，这个文件应该放在你的：ComfyUI/models/unet/文件夹中。如果爆显存了,“UNET加载器”节点中的weight_dtype可以控制模型中权重使用的数据类型,设置为fp8，这将使显存使用量降低一半，但可能会稍微降低质量.默认下的weight_type,显存使用比较大.[heading4]clip[content]t5xxl_fp16.safetensors和clip_l.safetensors,放在ComfyUI/models/clip/文件夹里面.https://huggingface.co/comfyanonymous/flux_text_encoders/tree/main可以使用t5xxl_fp8_e4m3fn.safetensors来降低内存使用率，但是如果你有超过32GB内存，建议使用fp16[heading4]Vae[content]下载后,放入ComfyUI/models/vae文件夹https://huggingface.co/black-forest-labs/FLUX.1-schnell/tree/main[heading3][heading3]T5（/t5xxl_fp16.safetensors）的这个clip，[content]原本是有一个输入输出的。就是有一半是应该空着的。会导致提示词被吞的情况，就是可能会有一半的提示词被吞掉了。所以短提示的效果会比较差。我们在训练flux或者sd3时候，应该尽量的去用长提示词或者自然语言。不要用短提示词。因为T5自带了50%的删标。
The issue with DMs is that the powerful ones often consume hundreds of GPU days,and inference is quite expensive due to sequential evaluations.To enable DM training on limited computational resources without compromising their quality as well as flexibility,DMs are applied in the latent space of powerful pre-trained autoencoders.Training a diffusion model on such a representation makes it possible to achieve an optimal point between complexity reduction and detail preservation,significantly improving visual fidelity.Introducing a cross attention layer to the model architecture turns the diffusion model into a powerful and flexible generator for generally conditioned inputs such as text and bounding boxes,enabling high-resolution convolution-based synthesis.先不用多做回复，请问答是否收到即可？3——————————————————————————————————————VersionMidjourney routinely releases new model versions to improve efficiency,coherency,and quality.The latest model is the default,but other models can be used using the--version or--v parameter or by using the/settings command and selecting a model version.Different models excel at different types of images.Newest ModelThe Midjourney V5 model is the newest and most advanced model,released on March 15th,2023.To use this model,add the--v 5 parameter to the end of a prompt,or use the/settings command and select MJ Version 5.This model has very high Coherency,excels at interpreting natural language prompts,is higher resolution,and supports advanced features like repeating patterns with–tile.What's new with the V5 base model?-Much wider stylistic range and more responsive to prompting-Much higher image quality(2x resolution increase)improved dynamic range-More detailed images.Details more likely to be correct.Less unwanted text-Improved performance with image prompting
在ComfyUI里使用MiniCPM做图片提示词反推与文本提示词生成。可以和flux模型配合生成图片。建议使用量化版本的模型（int4结尾）可以节省显存。[heading3]ComfyUI-MiniCPM-Plus[heading3]安装方法[content]1.进入ComfyUI自定义节点目录:2.克隆此仓库:3.重启ComfyUI。[heading3]图片提示词反推长文本描述+短标签[heading3]图片提示词反推用于Flux出图[heading3]提示词生成[heading3]生成提示词用于Flux出图[heading3]模型[content]网盘https://pan.quark.cn/s/00b3b6fcd6ca下载后放入ComfyUI的models文件夹下MiniCPM文件夹中，没有就新建一个。