Architects' tools
Открыть в Telegram
Hi, my name is Albert Sumin, this is my channel, I am an architect and computational designer at Cloud Cooperation (Vienna, Austria)
Больше719
Подписчики
Нет данных24 часа
+67 дней
+2730 дней
Загрузка данных...
Похожие каналы
Облако тегов
Нет данных
Возникли проблемы? Пожалуйста, обновите страницу или обратитесь к нашему support-менеджеру .
Входящие и исходящие упоминания
---
---
---
---
---
---
Привлечение подписчиков
январь '25
январь '25
+6
в 0 каналах
декабрь '24
+35
в 0 каналах
Get PRO
ноябрь '24
+83
в 1 каналах
Get PRO
октябрь '24
+60
в 0 каналах
Get PRO
сентябрь '24
+54
в 0 каналах
Get PRO
август '24
+503
в 0 каналах
Get PRO
июль '240
в 0 каналах
Get PRO
июнь '240
в 0 каналах
Get PRO
май '24
+1
в 1 каналах
| Дата | Привлечение подписчиков | Упоминания | Каналы | |
| 06 января | +1 | |||
| 05 января | +2 | |||
| 04 января | 0 | |||
| 03 января | +3 | |||
| 02 января | 0 | |||
| 01 января | 0 |
Посты канала
video with a demonstration of what we will do in my half of the class, and first, with Stepan, students will write code to generate a voxel model.
| 2 |  +3Tomorrow we (Stepan from SA lab and I) are running a short one-day workshop on the Design Morphine platform, and you still have time to sign up. it will be primarily for those who are just starting to dive into the topic of AI, i.e. the level of complexity is assumed to be basic. The workshop will be in English, here is the link:
https://designmorphine.com/education/cellular-diffusions-v1-0
#comfyui #education | 403 |
| 3 | Notion with description and links to comfyui desktop installers:
https://comfyorg.notion.site/ComfyUI-Desktop-User-Guide-1146d73d365080a49058e8d629772f0a | 364 |
| 4 |  #comfyui made an app that is simply installed on your computer, goodbye complicated instructions. for now they email it to those who signed up for the beta test, but probably soon you will be able to download it on the website. if you have an old installation, you can automatically connected models from it, but not custom nodes (coming soon), so you will have to install them separately. in my tests it works well except closing process, which I always need to end through the task manager. and it's not just for windows, for mac as well | 514 |
| 5 | +2 24_FluxDev_LORA+Upscale.json | 544 |
| 6 | there are workflows for #comfyui , on which I tested LORA models. | 466 |
| 7 |  +2The last thing I'd like to tell you about training LORA for Flux is an attempt to train something on top of a very curious model called OpenFLUX.1. The idea behind this model is that it is a fine-tuned version of Schnell, reconfigured to produce Flux Dev quality. Technically it's possible to train LORA on top of this model, but I wouldn't say I've been able to find good parameters. Here's the Colab that I've configured, if you experiment with it, please let me know what you find.
#comfyui #lora #flux | 455 |
| 8 |  +2I trained on the same dataset and with the same parameter variations as when using Dev model. in general, of course, the renders are a bit simpler, but Schnell, and everything you produced with it, can be used freely for commercial purposes. in addition, this model is noticeably less demanding on computer resources | 431 |
| 9 |  +2Let's talk about LORA training based on the Schnell model. in general, it's kind of impossible to do this because the model itself is not suitable for this task, but the developers from Ostris have prepared a special adapter that solves the problem. in the Google Colab code you need to additionally write a link to the model and the adapter, as well as replace the parameters for the test rendering. i've already done it, here's the link.
#comfyui #lora #flux | 429 |
| 10 |  Can Chat GPT be used to change information in a Revit model? Check out this video that Anatoly Razinkov prepared for our upcoming workshop on integrating AI into BIM.
This workshop will be in Russian, but if you are interested in the English version, leave a comment | 331 |
| 11 |  +1and here is another example. remember that the dataset was photos of Coop Himmelb(l)au projects. a conclusion can be that if a dataset with captions was used, elements of real buildings from the company's portfolio are literally borrowed. this can of course be leveled out by reducing the weight of lora when rendering or mixing it with other lora models. if there are no captions, then the general architectural style remains, but without precisely following the details. both can be needed in different situations. | 573 |
| 12 |  +1let's compare: these are renders with exactly the same prompts, seeds and all parameters, only lora is different. lora models were also trained on the same seeds and the same parameters, but for the first image lora is used, where in the dataset were captions, and for the second were only images (the images themselves are exactly the same as in the first dataset). | 465 |
| 13 | an interesting feature of model training for flux is that captions in the dataset are not necessary at all, just a folder with images is enough. the reason for this is the t5 encoder, which is somewhat llm (large language model), and can make captions itself. you may have noticed that t5 is also used in comfyui in flux algorithms along with the usual clip (familiar from sdxl and earlier versions of sd) , there it is needed to interpret your prompt more accurately, and in training to interpret captions or even make them.
#comfyui #lora #flux | 429 |
| 14 |  Just a simple thing from my #grasshopper course. Tomorrow we'll be back to FLUX loras | 342 |
| 15 |  +2there are some other nuances, we will look at them next time, but, in general, this information is enough to start working on training your own models. | 364 |
| 16 |  then go to the menu Runtime > Restart session and run all. at the first step Colab will ask you to connect to Google Drive, and then everything will go automatically, you only need to monitor the folder with results to watch test renders, and if something goes wrong, stop the process. to stop the process, choose the command Runtime > Disconnect and delete runtime. | 328 |
| 17 | If these parameters are configured, you can already start the learning process. select Runtime Type as shown in the screenshot. | 311 |
| 18 |  conten_or_style - a simple switch, it is obvious from the name, you can choose whether you prefer image style, content or both.
metainfo_name and metainfo_version - information that will be stitched into the model, these parameters do not affect the learning process.
image_width and image_height - resolution of images that will be used for test renders. it is reasonable to leave 1024x1024 here. | 314 |
| 19 |  The three parameters that most affect the learning process:
- network_rank is responsible for how many different details in the dataset images LORA will be able to memorize and then use. the higher the value of the parameter, the more attention to details, but also the weight of LORA in the end will be greater. thus, if the overall style of the image is important to you, rather than individual elements, then set something around 16 or 32. if details are important, then 64 or even 128.
- learning_rate is responsible for how quickly the model will be trained. the range of values here is from 0.0001 to 0.0015. the higher the value, the faster you will reach the state of the overtrained model. usually, the smaller your dataset is, the higher the learning_rate should be set, otherwise there is a risk that you will waste a lot of time and money. the risk is minor, because we have test renders and we can draw conclusions from them and stop the process. well, and through steps_number you can set the limit when the process will stop itself
- steps_number - the number of training steps. most often the optimal parameter value here for a dataset of 50 images is between 2000 and 4000 steps. | 279 |
| 20 |  next we have sample prompts. these prompts are used to generate images after a certain number of training steps (in our case, the default is that every 250 steps test renders will be run. Of course, it is better to write prompts that suit your purposes. I usually use one of them exactly as for one of the images in the dataset, i.e. copy the description, and the other two are random, but also on the topic of architecture. | 260 |
