newsans23

How to create Lora (Basic version)I believe that when creating an image you like, you may sometimes feel that some element is missing, and you may try to search for the relevant lora, but still cannot find it.At this time, you may think, should I make a lora myself? In this way, in my future works, maybe I can highlight more of the elements I like! I can also share it with my creative partners.Let’s get started!First, you need to collect more pictures of similar elements (about 12 pictures), and the picture resolution should be higher, so that when you use it with other LoRa in the future, the pictures will be clearer, unless the element you want is a hazy feeling.Next, it’s time to start training!First, open the user interface and there is a model I trained. Then click the online training in the upper left corner to enter the training interface. Add the prepared image in the lower left corner. Select the basic model type you often use in the upper right corner, such as: sd1.5, sd3.5, pony, flux, Hunyuan, etc.Next, you need to consider your computing power budget, because if you use different basic models to train the same image, the results will be very different, and the computing power consumption will also be different. Also, can you use it together with the commonly used LoRa?For the trigger word part, you can input the most important elements of this lora. You can choose not to input them first and wait until you see the training results.The prompt word part seems to affect the training results. If you have a clear goal, you can enter it. The default is 1girl. If your element is not a girl, you can change it or leave it blank.OK, next click on training, wait in line and check the training time.After the training is finished, I will look at the training results. There are ten training results in total. I usually choose one from the sixth to the tenth one that looks closer to the result I want and press publish.Select Create Project at the top.Enter the project name (be careful, this cannot be changed)Select Lora TypeAdd lora tagparameterI usually choose 500 for the number of iterations.Type the trigger word and descriptionSelecting a base modelReverse prompt wordUpload files unless they are the result of previous trainingOtherwise, I usually adjust the precision to fp32.Showcases (Image/Video)If you are uploading the results of a previous training, you need to upload the workbench image and cover imageOK, press PublishAdjust the details again, update and wait for the system to be deployed, then you can try it out and see your results!😁😁😁

Build guideAs a player who has used tensor art for more than half a year to generate images with AI,First of all, when I first want to generate pictures, most of them have no inspiration or don’t know how to command keywords.Because the "Daily Theme" button has appeared recently, you can click it to see if the theme arranged today meets your interests. Then look at the works of other masters. If you like it, you can try pressing the blue button below the picture. Button "make the same style",At this time, you will enter the online drawing state.At the top of the screen are the keywords used in the picture just now.On the upper left is the basic model he uses, and below is the correction module "Lora" he attached, also known as style. The combination of the basic model + Lora is the most interesting part of tensor art for me. It is obviously using The same keywords, but very different results due to different combinations.You can usually look at pictures of a style you like more and mark them using the basic model and lora. Then next time you want to make a picture of a similar style, you can use it from my markup.Looking further down is the picture size, followed by portrait, landscape, square and any.Below is a random seed, or a specific seed. If you want to generate an image that is almost the same as the original image, you can copy the seed number and paste it directly.Looking further down is the high-definition restorationHere you can increase the resolution of the image. The higher the resolution, the more detailed the image will be and the larger the image will be. However, if your module itself cannot support such a high resolution, the image will be broken or become gridded. shape.Further down is ADetailerLora can be used to correct hands, feet and faceI think this function is very useful.But it is currently only available in the SD1.5 part.Some Loras are trained as a specific person.Then if you use the function here,The picture will look very much like the person.The above is my experience of using it for more than half a year. Hope this helps you! !Below are the keywords I used to generate the cover imageScore_9,Hero movie style. During the day, Venom merges with Pumpkin Man. Fast and powerful poisonous pumpkins leap between walls. Strong muscles and great strength, showing his destructive power.Extreme Detail, Cinematic Shots, Photorealistic Illustrations, (Soothing Tone: 1.3), (Ultra Detailed: 1.2), Masterpiece, RAW, Best Quality), (Vivid Colors: 1.3), Best Quality, Masterpiece, Beauty & Aesthetics, 16K, (HDR: 1.4), High Contrast, (Vivid Colors: 1.4), (Quiet Colors, Dull Colors, Soothing Colors: 0), Cinematic Lighting, Ambient Lighting, Side Lighting, Fine Details and Textures, Cinematic Lens, Warm, Full Body (Bright Intense: 1.2)), (Masterpiece, Top Quality, Best Quality, Official Art, Beautiful: 1.2), HDR, High Contrast, Wide Angle Lens (High Detail) Skin: 1.2) (Hero Movie Theme , followed by a damaged pumpkin and a tumbled pumpkin).