AI Search
@aisearchio

Sharing AI stuff 🚀 740K subs Nature lover, PhD, investor, shitposter piped.video/@theAIsearch

 The Future
piped.video/@theAIsearch
Joined February 2023
1,753 Photos and videos
What a crazy week in AI! 🚀 Gemini 3.8 Live Qwen 3.8 Omni Flash Qwen 3.8 Live Translate Bonsai 2 27B Needle 3 Jev Laya Nimble Occamy ZGCM Meridian R2T2 Jing Dao Dream RSI MiniMax Code & more! Watch the full recap: piped.video/hygMRgnDD7w
9
7
175
11,600
Another frontier video model coming soon. Curious to see how it compares to Seedance.
18
4
179
9,542
AI Search retweeted
ViggleAI
@ViggleAI
16h
🚀 Viggle Turbo v0.2 is out! Text-to-image and image editing in 6 steps: about 5× faster than the 40-step Qwen-Image-2.1. Run it for free: huggingface.co/spaces/Viggle…

Viggle Turbo v0.1 - 4-step Qwen-Image-2.1 - a Hugging Face Space by Viggle

v0.1 preview - 4-step Qwen-Image-2.1, T2I + editing

huggingface.co
Yun Chen
@t_mux
16h
viggle-turbo for Qwen-Image-2.1 isn't just faster — for most prompts, it's just as good as base.
5
8
88
9,855
Stumbled upon this cute platform by Google, called Gemini Worlds, I assume. Nice visual resource for learning about different topics in science and history. gemini.google.com/worlds
2
2
48
3,118
Lots of useful stuff for Minimax H3 here, like upscaler, head swap, style transfer, vfx edit. huggingface.co/Alissonerdx/M…
5
7
227
9,698
Minimax H3 character swap lora. Dataset included! huggingface.co/akatz-ai/Mini…
2
18
383
14,782
Airbnb listing to full VR property tour in Blender Claude Opus 5.5 full review piped.video/gX0L0aFA2xg
3
2
56
4,349
OpenAI: Introducing the world's best model Anthropic: Introducing the world's best model Google: Introducing Gemini 3.8 Flash TTS 😃😃😃
45
21
868
23,653
Qwen Image 2.1 viggle turbo. This generates images in only 4 steps instead of 40, making it way faster huggingface.co/Viggle/Qwen-I…
19
24
424
21,899
Opus 5.5 has failed the frog test
39
2
246
12,069
Well, hello there
19
2
231
7,804
Run Qwen Image 2.1 on AMD, Intel, Mac with as little as 2GB VRAM. No CUDA required github.com/nihui/qwenimage-n…
16
60
824
40,900
Opus 5.5 is out now. OpenAI & Google will also likely drop something soon. It's only Tuesday 😭
AI Search
@aisearchio
Sep 22
New Opus possibly dropping this week
18
2
205
7,137
Some attention and acceleration notes for Qwen Image 2.1. Can save a few dozen seconds per generation, depending on your hardware. github.com/awdqwdasdg/Comfyu…
11
29
493
34,087
Qwen Image 2.1 latent upscaler. This allows you to gen at low resolution in the first pass, which will be upscaled to higher resolution in the second pass. The base model is already quite fast, so this might only save a few seconds. github.com/kinfolk0117/Comfy…
2
11
250
11,166
Finally done Qwen Image 2.1 review & tutorial: piped.video/BaE6UBfNdQk My thoughts so far: Krea2 is better for t2i but Qwen is the best open edit model. The ideal workflow is generating images in Krea, then refining them in Qwen if needed.
12
4
214
10,874
New Opus possibly dropping this week
5
1
54
11,681
More Qwen Image 2.1 tests
4
103
10,288
More Qwen Image 2.1 tests
AI Search
@aisearchio
Sep 21
Qwen Image 2.1 vs Krea 2
5
109
17,340
Qwen Image 2.1 vs Krea 2
31
11
295
53,662
AI Search retweeted
zR
@zRdianjiao
Sep 21
ZCode is now open source under the Apache 2.0 license. github.com/zai-org/ZCode

GitHub - zai-org/ZCode: Z.ai's coding agent harness. Powerful, intelligent, extensible.

Z.ai's coding agent harness. Powerful, intelligent, extensible. - zai-org/ZCode

github.com
97
159
1,392
241,757
Load more