Stable Diffusion online AI
@ai_diffusion
AI-generated 🖼️🎬• Large Language Models ✒️ • open-source https://linktr.ee/stable.diffusion
Potrebbero piacerti
Make sure to update Grok every day. I notice improvement of the model between major releases.
The next wave of animation won't come from studios. It'll come from bedrooms. I'm calling it now: 2026 is the year of homemade anime. Thousands of shows, all created by solo creators. Think about it: Traditional animation: 50+ people per episode $500K-2M budget 9-18…
Enjoy your coffee, weekend and create something awesome 🥹🫶 Also remember: you’re excellent!
We’re updating olmOCR, our model for turning PDFs & scans into clean text with support for tables, equations, handwriting, & more. olmOCR 2 uses synthetic data + unit tests as verifiable rewards to reach state-of-the-art performance on challenging documents. 🧵
Create surreal art that doesn’t exist I’d love to see. Here’s mine.
☕️ 🏝️ have a nice day!
LET’S GOOO 🔥 Just released Smol2Operator, a full open-source recipe for turning a 2.2B model into an agentic GUI coder, and all the tools you need to build your own 🫡
Cartoon Hero x WaveSpeed AI animation contest 🔥 Create an AI animation short and win up to $500 in WaveSpeed credits! The contest is open to EVERYONE. Rules 👇
2/2 Try it now！ • wan.video • GitHub：github.com/Wan-Video/Wan2… • ModelScope：modelscope.cn/models/Wan-AI/… • Hugging Face Space：huggingface.co/spaces/Wan-AI/…
📹 Qwen image edit fp8 + Wan 2.2 fp8 + lightx2v 8steps lora 🔥 🗺workflow: github.com/camenduru/Wan2…
large AI labs open-sourced a ton of models last week 🔥 here's few picks, find even more on the next one 🤝 > IBM released a new Docling model with 258M params based on Granite (A2.0) 📝 > Xiaomi released 7B audio LM with base and instruct variants (MIT) > DecartAI released…
Wan 2.2 Animate is actually Crazy!! You can replace characters from a simple source image. No need to first frame anymore. It handles facial expressions and body movements like no other model I have ever seen. It is open source and free to use, that's the crazy part!
upgrade your transformers 🔥 it comes with insanely capable models like SAM2, KOSMOS2.5, Florence-2 and more 🤝 I built a notebook you can run with free Colab T4 to walk through the API for new models 🙋🏻♀️ fine-tuning will follow-up soon!
I imagine a future where your cartoon characters have their own socials (IG, X, TikTok, etc.) sharing their daily "behind the scenes" content just like actors do in real world. Just think how wild that would be.
Today, we are releasing FineVision, a huge open-source dataset for training state-of-the-art Vision-Language Models: > 17.3M images > 24.3M samples > 88.9M turns > 9.5B answer tokens Here are my favourite findings:
This is so cool 😍
Since I'm doing @0xFramer Cartoon Hero course, I asked my son what kind of cartoon he wanted and we decided on a kid detective solving a case. Here is the 10-second result.
This is so cool.
Generative AI enables new formats of storytelling. Here’s an example of a new type of video you can create with AI tools. Workflow with prompts ⤵️
"The Last Throne” ⚔️ Time spent: 3h40min Cost: $8.20 The biggest shift in creativity has started. Now anyone can tell stories through insane, studio-quality animations. Here’s how 👇
Okay this is insane... WebGPU-accelerated semantic video tracking, powered by DINOv3 and Transformers.js! 🤯 This will revolutionize AI-powered video editors... which can now run 100% locally in your browser, no server inference required (costs $0)! 😍 Who's building this?
United States Tendenze
- 1. #AEWDynamite 19K posts
- 2. #AEWCollision 7,230 posts
- 3. #CMAawards 4,676 posts
- 4. Philon N/A
- 5. #Survivor49 3,257 posts
- 6. Donovan Mitchell 3,720 posts
- 7. #cma2025 N/A
- 8. Dubon 3,286 posts
- 9. Simon Walker N/A
- 10. Nick Allen 1,960 posts
- 11. Okada 12K posts
- 12. UConn 7,716 posts
- 13. Lainey Wilson N/A
- 14. Derik Queen 1,673 posts
- 15. Bristow N/A
- 16. Cavs 8,374 posts
- 17. Arizona 31.7K posts
- 18. Morgan Wallen N/A
- 19. FEMA 53.9K posts
- 20. Andrej Stojakovic N/A
Potrebbero piacerti
-
Princeton Vision & Learning Lab
@PrincetonVL -
DynamicWang
@dynamicwangs -
AsymTrading
@AsymTrading -
Inspiration Wiz
@Inspirationwiz -
AI News by Smol AI
@Smol_AI -
GPTDAOCN-e/acc
@GPTDAOCN -
熊猫 AI 🐼
@OxPanda_ -
Div Garg
@DivGarg_ -
Superstudio
@KaiberAI -
vigorxu
@vigorX777 -
miggi from figgi
@miggi -
James Campbell
@jam3scampbell -
AI Tutor
@myaitutor -
Murf AI
@MurfAIStudio -
stephen balaban
@stephenbalaban
Something went wrong.
Something went wrong.