- 22
- 47 284
Prateek Joshi
India
เข้าร่วมเมื่อ 23 ม.ค. 2014
Hey, this is Prateek. I'm an AI engineer with years of hands-on experience in Python, Machine Learning, Natural Language Processing (NLP), Data Visualization, and Generative AI.
Differential Diffusion Inpainting with Diffusers in Python
Python tutorial to implement differential diffusion driven inpainting.
Code - github.com/prateekjoshi565/Differential-Diffusion
Community Pipelines - github.com/huggingface/diffusers/tree/main/examples/community
Code - github.com/prateekjoshi565/Differential-Diffusion
Community Pipelines - github.com/huggingface/diffusers/tree/main/examples/community
มุมมอง: 66
วีดีโอ
Extract Tables from Image Documents | Florence-2 Model | Python
มุมมอง 131วันที่ผ่านมา
Code - github.com/prateekjoshi565/Table-Detection/blob/main/Florence_Table_Extraction_code.ipynb Fine-tuned Florence-2 model - huggingface.co/ucsahin/Florence-2-large-TableDetection
Style Transfer with Stable Diffusion in Python | Diffusers
มุมมอง 8514 วันที่ผ่านมา
In this tutorial, we will perform style transfer with the help of a Stable Diffusion model, ControlNet and IP-Adapter. Python code - pjoshi15.com/how-to-perform-style-transfer-with-stable-diffusion-and-python/
Florence-2 for Data Labeling in Python
มุมมอง 1.6Kหลายเดือนก่อน
In this video, I am using Microsoft's foundation vision model Florence-2 to label images for multiple computer vision tasks. Code - github.com/prateekjoshi565/florence-2-data-labeling Florence-2 technical report - arxiv.org/abs/2311.06242
Guided Image Generation - ControlNet and SDXL Flash in Python
มุมมอง 205หลายเดือนก่อน
In this tutorial, I use Depth Anything model to estimate depth in an image and then use the depth information in a "ControlNet SDXL Flash diffusion" pipeline for guided and controlled image generation. Tools used - Python, Kaggle Notebook
Generate Image Descriptions using Gemini Flash
มุมมอง 93หลายเดือนก่อน
A hands-on tutorial to perform image description generation (or image captioning) with Gemini's API and Python. Create your API key here - aistudio.google.com/
SDXL Flash - A fast model with better image quality
มุมมอง 142หลายเดือนก่อน
In the video, I load and run the SDXL Flash model in a Kaggle notebook. I have used Python and the Diffusers library for image generation. SDXL Flash page - huggingface.co/sd-community/sdxl-flash
Build AI Image Generation Web App with Anvil - Part 2
มุมมอง 202 หลายเดือนก่อน
This is the second video where we build an Anvil app powered by a Stable Diffusion API for image art generation. Part 1 - th-cam.com/video/CbBf6uV-PqE/w-d-xo.html Create account at Getimg AI - getimg.ai/?via=pjoshi GetImg API Documentation - docs.getimg.ai/reference/introduction
Build AI Image Generation Web App with Anvil - Part 1
มุมมอง 332 หลายเดือนก่อน
In this hands-on tutorial, I create a web app in Anvil platform from scratch. This web app uses an image generation API to generate images based on prompts provided by the user. Part 2 - th-cam.com/video/2nxp7X0uJ7g/w-d-xo.html Create account at Getimg AI - getimg.ai/?via=pjoshi GetImg API Documentation - docs.getimg.ai/reference/introduction Code - pjoshi15.gumroad.com/l/jgmes If you want to l...
Image-to-Image Generation with Stable Diffusion API | Getimg AI
มุมมอง 1353 หลายเดือนก่อน
Perform image-to-image generation using a Stable Diffusion API provided by Getimg AI in Python. Create account at Getimg AI - getimg.ai/?via=pjoshi Python notebook - pjoshi15.gumroad.com/l/cfmyu Getimg AI API Documentation - docs.getimg.ai/reference/introduction Text-to-Image generation - th-cam.com/video/wTnkaynSIEc/w-d-xo.html
Stable Diffusion Image Generation - Python GetImg API Tutorial
มุมมอง 1003 หลายเดือนก่อน
In this video, get an overview of the GetImg AI platform and learn to use the API of GetImag AI for text-to-image generation in Python. Create account at Getimg AI - getimg.ai/?via=pjoshi Code notebook - pjoshi15.gumroad.com/l/cfmyu API docs - docs.getimg.ai/reference/introduction
How To Use SDXL Lightning In Python - Stable Diffusion
มุมมอง 4095 หลายเดือนก่อน
In this tutorial I use the blazing fast SDXL Lightning model with Diffusers library for fast image generation. Using Stable Diffusion models with Python can help you to work on a wide range of real world use-cases. SDXL Lightning repository - huggingface.co/ByteDance/SDXL-Lightning Code Notebook - github.com/prateekjoshi565/sdxl-lightning/blob/main/SDXL_Lightning.ipynb
Change Clothes Using AI - Stable Diffusion | SAM | Diffusers | Python
มุมมอง 3525 หลายเดือนก่อน
In this tutorial, I have used SlimSAM model and Stable Diffusion Inpainting to change and edit clothes of a person in an image. Python code - pjoshi15.com/change-clothes-stable-diffusion-sam/
SDXL Turbo Image Generation in Python
มุมมอง 1826 หลายเดือนก่อน
In this tutorial, you will learn to use SDXL Turbo model for text-to-image and image-to-image generation in Python. Python code - pjoshi15.com/img2img-sdxl-turbo-python
How to add VIDEO inside TEXT | Python Tutorial
มุมมอง 677 หลายเดือนก่อน
In this tutorial, I will teach you to put a video inside text using Python. The video will play in the background but it will be visible only through the overlaid text. Code - pjoshi15.com/video-inside-text/ Important All video material, music and sound effects are protected by copyright. Unauthorized use and distribution of the video is not permitted.
Add Text Behind Moving Objects Using Python
มุมมอง 967 หลายเดือนก่อน
Add Text Behind Moving Objects Using Python
Automatically Remove Colors from Vector Graphics
มุมมอง 4382 ปีที่แล้ว
Automatically Remove Colors from Vector Graphics
Fine-Tuning BERT on Colab to Perform Spam Classification
มุมมอง 1.5K3 ปีที่แล้ว
Fine-Tuning BERT on Colab to Perform Spam Classification
How would you suggest fine tuning this on your own data?
Great tutorial. Thank you. You got yourself a Like and Subscribe from me. Could you also provide us with access to the source code itself, it would mean a lot.
Thanks for subscribing! I have added the code in the description.
@@pjoshi_15 Thanks.
Can you please share the code for this project?
thank you
nice vid bud , excellent work
Very helpful as always, thank you!
Thanks once again, Prateek! P.S: Still waiting for a video showing how to host SDXL Flash on a cloud GPU to enable access via an API! 🙂 more power to you!
Another great video ✨
You produce such amazing videos!!! Super helpful, on point - Crisp! I am sure by the end of this year, you will exceed 1000's of followers (still cannot believe you are on 65 only) I'd love to see a video, in your crisp style, showing how to host SDXL Flash on a cloud GPU to enable access via an API! Would really help people getting started, make sense of the landscape.
Thanks Ameer for the kind words 🙂 I'll try to publish more videos on SDXL Flash and Cloud hosting.
@@pjoshi_15 Eagerly look forward to those!
when I run script, I get error: outofmemory even though i also run on collab: input_points_2 = [[[200, 850]]] inputs_2 = processor(img, input_points=input_points_2, return_tensors="pt").to("cuda") outputs_2 = model(**inputs_2) masks_2 = processor.image_processor.post_process_masks(outputs_2.pred_masks.cpu(), inputs["original_sizes"].cpu(), inputs["reshaped_input_sizes"].cpu()),
Thank you @Prateek Joshi for this useful knowledge.
worked, but the model is crap lol. I want to use this method to content automation but I dont think it will work
Thank you bro. It was greate
Really good and on point explanation. wish to see more tutorials related to hugging face models.
Thanks for taking the time to make this tutorial. I'm new to all of this and you did a good job explaining the paramters.
hi how are you >>>>How do you calculate the total number of cars and where will you put the code
Hi, I simply use the number of contours below the highlighted horizontal line to count the detected vehicles. Hope it helps!
@@pjoshi_15 yes bro i see thats but i mean the totals numbers of all cars with 24 h for exe.
@@pjoshi_15 ples answer me how can i contact you bro
Nice and simple tutorial