IF (@ImpactFramesX) header
IF (@ImpactFramesX) profile picture

AI/ML researcher

Joined August 2020
Photo by IF (@ImpactFramesX)Photo by IF (@ImpactFramesX)Photo by IF (@ImpactFramesX)Photo by IF (@ImpactFramesX)Photo by IF (@ImpactFramesX)Photo by IF (@ImpactFramesX)Photo by IF (@ImpactFramesX)Photo by IF (@ImpactFramesX)
Creator of free Adobe clones unveils open-source Microsoft Office Excel, PowerPoint, and Word replications tomshardware.com/software/mi…
162
723
202
3,826
648,908
OpenRouter for generative media is here 🦾
Comfy Router is live One API for frontier image, video, 3D, and audio models. Same model string. Same arguments. No new SDK, no new key, no redeploy. What Comfy Router gives you: → Explicit routing. You name the provider, we call that provider. It's down? The request fails there. No silent fallback. → Every job returns the provider that ran it. Log it, bill it, debug it. → Async. submit() returns a request ID immediately. The queue retries 429s and transient errors until a slot opens. subscribe() submits and polls to completion. → Batch-friendly. Queue a few hundred jobs, hold the IDs, pull results as they land. Nothing blocking on a 5-min video render. → 24h retention on inputs and outputs, then deleted. → Comfy credits. No sub, no Router fee. Providers at launch: Comfy. Runware, Wavespeed, Fal, Higgsfield. Multi-provider where the model supports it. Get Your API Key with the link below. ⬇️
7
14
1
118
19,006
Qwen-Image-2.1 is now supported in ComfyUI! Try it now and share your creations! 🖼️
Qwen-Image-2.1 is now supported in ComfyUI! Open weights. One 7B checkpoint that generates and edits. → Image generation at native 2K → Instruction editing from up to 10 reference images in a single pass → RGBA output, alpha included
46
82
13
1,281
114,655
Google is letting its employees use Claude. 💀
79
81
8
3,027
85,879
Dear Lord, please bless my mom. Alwayyyyyyyyyyyys.
13
513
9
4,832
52,547
Today, we’re announcing Ternary Bonsai 2 27B. Based on Qwen3.8 27B, Bonsai 2 27B is 9x smaller than its full-precision counterpart while retaining 98.2% of its aggregate benchmark performance. Two months after the first Bonsai 27B release, the biggest change is quality. The footprint remains 5.9 GB, but the gap to full precision has narrowed materially, with particularly strong gains in agentic coding, multimodal reasoning, and long-horizon tool use. Ternary Bonsai 2 27B is available today under Apache 2.0.
637
1,562
786
15,519
5,483,035
😅
136
313
29
1,503
18,679
This guy knows ball:
29
696
9
4,690
108,889
126
8,726
179
83,433
938,581
IF retweeted
Replying to @techdevnotes
Grok 4.8, which is a 2.5T model trained with our new C++ software stack, will finish training this week and start RL
8
43
1
1,455
34,731
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions AFAICT the shortest path to AI-based economic revolution
4,022
8,274
6,820
76,591
40,146,187
IF retweeted
74
982
57
9,918
350,241
In 9 days, OpenAI switches off the Sora 2 API. Sept 24: sora-2, sora-2-pro, every snapshot. Gone. If your workflow was prompt in, clip out, you're rebuilding. If the model was one node, you're swapping it. Models are rentals. Workflows are property.
5
6
45
7,225
Bracing for the tsunami of Woke 2 NPCs lecturing on the dangers of AI because they watched a TikTok reel and a Netflix doc. IG stories will be insufferable through this election cycle. Ugh. What hath the EAs wrought?
1
1
61
48
171
27
1,671
223,253
FLUX 3 🧐 🥲
9
9
3
202
13,138
Real-time audio led video generation in H3 Director is just too fun
3
2
13
1,040
I tested De-RoPE in ComfyUI to reduce motion smearing in MiniMax H3. Side-by-side results, what improved, and what still breaks. Watch: youtu.be/IlVPJI9ceKM
4
6
49
3,414