Prithiv Sakthi PRO

prithivMLmods

AI & ML interests

Computer Vision | Prompting | Diffusion | Data Science | Web Product Production | GenAI

Organizations

Posts 6

view post
Post
2207
๐Ÿ”ดโญ New addition to the existing concept space! ๐Ÿ”ดโญ

๐Ÿž๏ธ Space: prithivMLmods/IMAGINEO-4K

๐Ÿš€ Tried the Duotone Canvas with the image generator. Unlike the duotone filter in the Canva app, which applies hue and tints in RGBA, this feature applies duotones based purely on the provided prompt to personalize the generated image.

๐Ÿš€ These tones also work with the gridding option, which already exists in the space.

๐Ÿš€ The application of tones depends on the quality and detail of the prompt given. The palette may be distorted in some cases.

๐Ÿš€It doesn't apply like a hue or tint in RGBA (as shown in canva app below); it is purely based on the prompts passed.

๐Ÿž๏ธ Check out the space: prithivMLmods/IMAGINEO-4K
๐Ÿœ๏ธCollection: prithivMLmods/collection-zero-65e48a7dd8212873836ceca2

huggingface.co/spaces/prithivMLmods/IMAGINEO-4K

๐Ÿž๏ธWhat you can do with this space:
โœ… Compose Image Grid
๐Ÿ‘‰๐Ÿป "2x1", "1x2", "2x2", "2x3", "3x2", "1x1"
โœ… Apply styles
โœ… Set up Image tones
โœ… Apply filters & adjust quality

.
.
.
Thanks for reading!
- @prithivMLmods
view post
Post
2553
๐Ÿšจ New Release: ultralytics8.2.51
๐ŸบLive Space : prithivMLmods/YOLO-VIDEO , Duplicate the Space to avoid queuing issues.
๐ŸบT4 Colab : https://colab.research.google.com/drive/1BKgFUfk2Me1cSPFmbtZSVCn_4cYImPO-?au
๐Ÿ‘‰๐ŸปFor HPC, use A100/T4 under controlled conditions.
๐Ÿ‘‰๐ŸปSpeed Estimation, Object Counting, Distance Calculation, Workout Monitoring, Heatmaps,etc.

Ultralytics dropped the YOLOv8 - #Ultralytics 8.2.51 ๐Ÿ”ฅ, YOLOv8 is designed to be fast, accurate, and easy to use, making it an excellent choice for a wide range of object detection and tracking, instance segmentation, image classification and pose estimation tasks.

๐Ÿ”— https://pypi.org/project/ultralytics/8.2.58/

๐Ÿš€More Features You can try:
โœ… Classes selection support added
โœ… Live FPS display in the sidebar
โœ… Webcam and video support added
โœ… Confidence and NMS threshold option to modify.
โœ… Segmentation, detection, and pose models support added.

๐Ÿ™€Ultralytics Live inference: https://docs.ultralytics.com/guides/streamlit-live-inference/
from ultralytics import solutions
solutions.inference()
### Make sure to run the file using command `streamlit run <file-name.py>`

โšกyolo streamlit-predict

๐Ÿ‘‰๐ŸปAdvantages of Live Inference

โ˜‘๏ธ Seamless Real-Time Object Detection: Streamlit combined with YOLOv8 enables real-time object detection directly from your webcam feed. This allows for immediate analysis and insights, making it ideal for applications requiring instant feedback.
โ˜‘๏ธEfficient Resource Utilization: YOLOv8 optimized algorithm ensure high-speed processing with minimal computational resources.
๐Ÿ™€Ultralytics feature Models: https://docs.ultralytics.com/models/, Ultralytics new Solutions: https://docs.ultralytics.com/solutions/

๐Ÿ‘‰๐ŸปOfficial Documentation:
Ultralytics YOLOv8 Documentation: Refer to the official YOLOv8 documentation for comprehensive guides and insights on various computer vision tasks and projects. ๐Ÿ”— https://docs.ultralytics.com/