@aisearchio

Sharing AI stuff 🚀 760K subs Nature lover, PhD, investor, shitposter https://xitter.cf/t.co/0Ms1yEyG5f

 The Future
youtube.com/@theAIsearch
Joined February 2023
  • Tweets3.4K
  • Following345
  • Followers27.5K
1.8KMedia
What a crazy week in AI! 🚀 Gemini 4 Argon Drama 3 Krea 3 MOSS-Image Matrix-Game 4 Kling 4 GaussiAnimate UniForge 3D Muse Wonder Muse Spark Open InfiniSplat v2 Step 5 Preview NVIDIA Nemotron 3.5 Super VL Ling-3.1-flash LFM2.5 RP1 & more! Watch the full recap: youtu.be/tDWtcyeNNew
16
19
1
310
12,513
Acceleration loras for Minimax H3 ref2va huggingface.co/taobao-conten…
3
2
49
2,528
AI Search retweeted
Hao AI Lab
@haoailabOct 20
As promised, FastVideo open-sources @MiniMax_AI FastH3 Omni, training code included! 🚀 - Real-time gen @ 12x faster on NVIDIA Blackwell - NVFP4/FP8 for Spark + RTX! - ComfyUI day-0 Collab with @NVIDIAAI , Nuva Lab @nuvalab and Reactor @reactorworld Open source must win! ♥️
31
68
45
599
59,269
If I ever want to smash my annoying neighbor's car, this is a good option without being held liable
Unitree
@UnitreeRoboticsOct 21
Unitree Introducing: H2-X Kung Fu Legend Guardian🤖 Powerful performance to serve and guard you, with a maximum endurance of approximately 8 hours. Please use the robot safely and in a friendly manner.
6
60
3,511
Clever hack to use MOSS with reference images github.com/ThetaCursed/Comfy…
5
23
375
17,225
Fibo 2.0 for ComfyUI huggingface.co/Comfy-Org/Fib…
6
11
187
9,172
AI Search retweeted
Krea
@krea_aiOct 20
today, Krea 3 makes it to the top of image arenas. - "Fast" pushes the pareto curve of speed and quality. - "Ultra" ranks top-4, only surpassed by OpenAI models. the only company valued under $1T in the top-10! more below 👇
117
188
159
1,625
1,269,725
AI never sleeps. I just finished the video on MOSS, and now we have a new image EDIT model, Fibo 2.0. Apparently it's the #1 open image edit model. Testing it out today. huggingface.co/briaai/Fibo-2…
19
32
3
520
20,583
MOSS Image knowledge test Full tutorial here youtu.be/cUeZMUGCxrw
8
12
269
11,929
Spectrum node for MOSS Image. Up to 2.5x speedup with no noticeable quality loss github.com/Rkkss/ComfyUI-Spe…
3
16
243
11,341
Kromoss, a new finetune of MOSS Image for even better quality and consistency huggingface.co/lodestones/Kr…
4
21
277
10,640
New model from Deepseek. 77 on DeepSWE!
DeepSeek
@deepseek_aiOct 17
🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API. 🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model. 1/4
4
3
182
6,720
The choice of demo images from the MOSS Image team 🤣
32
11
3
573
30,027
MOSS Image 8 step finetune is here. ~5x speedup compared with the base model (50 steps). huggingface.co/lodestones/MO…
7
19
3
272
11,816
New Minimax H3 character swap v1.5 huggingface.co/akatz-ai/Mini…
5
28
2
554
24,889
Now THIS is a good image model. MOSS Image, 5B Apache 2.0. Already very uncensored! huggingface.co/OpenMOSS-Team… huggingface.co/OpenMOSS-Team…
41
172
9
2,150
100,677
Kling 4 is also out today. AI never sleeps
10
5
231
7,339
To clarify, I remain optimistic about Flux 3 Klein. Most of these issues could be solved with (corn) checkpoints or loras. The previous Flux Klein with loras had been my go-to edit model for a while. Hopefully Flux 3 finetunes can exceed this.
AI Search
@aisearchioOct 15
Flux 3 Klein is more censored than Qwen 2.1, and has some occasional anatomy issues. Not impressed so far
9
138
8,749
Drama 3 by Fish Audio is now the top open TTS model. Allows meta tags within your transcript to control emotion, direction, SFX. Pretty good at voice cloning too. huggingface.co/fishaudio/dra…
20
30
2
512
22,083
New TaoMate H3 lora for speeding up Minimax H3 in ComfyUI huggingface.co/Robert1212sta…
5
8
1
214
10,912
Load more