NewCurious how Socialpruf works?Learn more
X analytics
Similar Accounts:
followers
7.46K
impressions
4.29M
likes
31.9K
comments
1.91K
posts
590
engagement
0.789%
emv
$96.2K
Average per post
7.28K

Key Metrics

Distributions

Top Content

Motion Prompt guide for @fal MiniMax H3 MAX is live! I added a bunch of examples too, so you can just copy the prompts and tweak them however you want. More prompting guides for this model are coming soon. x.com/i/article/209313103…

625K
872
37
100
1w ago
ailker
Motion Prompt guide for @fal MiniMax H3 MAX is live! I added a bunch of examples too, so you can just copy the prompts and tweak them however you want. More prompting guides for this model are coming soon. https://x.com/i/article/2093131035156357120
Don’t sleep on the new @fal auto-subtitle endpoint, I think it’s a really solid way to get tiktok-style captions on your videos.
232K
327
16
22
10mo ago
ailker
Don’t sleep on the new @fal auto-subtitle endpoint, I think it’s a really solid way to get tiktok-style captions on your videos.
For those wondering how it compares to Myhtos
199K
1.08K
45
42
4mo ago
ailker
For those wondering how it compares to Myhtos
Realistic iPhone photo taken at 48°51′24″N 2°21′03″E on July 14, 1789. Crowd perspective
197K
2.85K
35
126
8mo ago
ailker
Realistic iPhone photo taken at 48°51′24″N 2°21′03″E on July 14, 1789. Crowd perspective
Found a way to make nano-banana-pro insanely cost-effective on @fal I built a workflow that generates 9 4K images for a total of $0.21. That’s just $0.023 per image. That is a ~92% cost reduction. The key is grid generation. I added a 'Crop Node' as a workflow utility specifically for this. It takes the grid output, splits it, and then we upscale everything using SeedVR
148K
1.48K
61
86
9mo ago
ailker
Found a way to make nano-banana-pro insanely cost-effective on @fal I built a workflow that generates 9 4K images for a total of $0.21. That’s just $0.023 per image. That is a ~92% cost reduction. The key is grid generation. I added a 'Crop Node' as a workflow utility specifically for this. It takes the grid output, splits it, and then we upscale everything using SeedVR

I don’t get excited easily. But it really feels like we’re just days away from crossing a major threshold in one of the hardest problems for video models.

138K
496
74
26
9mo ago
ailker
I don’t get excited easily. But it really feels like we’re just days away from crossing a major threshold in one of the hardest problems for video models.
Is there any other industry where so many innovations come out every day as in Generative Media?
111K
1.20K
35
111
11mo ago
ailker
Is there any other industry where so many innovations come out every day as in Generative Media?
We’ve just added another natural-looking and realistic model 😱
92.4K
267
18
11
11mo ago
ailker
We’ve just added another natural-looking and realistic model 😱
and yes, I didn't make a single edit to this.
83.3K
311
18
12
2w ago
ailker
and yes, I didn't make a single edit to this.
📷 a new GPT Image 2 use case: text-to-360 turn text or an image into a 360° panorama.
81.3K
446
15
38
4mo ago
ailker
📷 a new GPT Image 2 use case: text-to-360 turn text or an image into a 360° panorama.
I created nearly 50 different use-case scenarios for Seedream and compared them with image-editing models. (I'll share them all over time) I think one of its strongest points is its ability to process depthmaps realistically. Is there a scenario you'd like me to compare with other models?
79.3K
452
23
46
12mo ago
ailker
I created nearly 50 different use-case scenarios for Seedream and compared them with image-editing models. (I'll share them all over time) I think one of its strongest points is its ability to process depthmaps realistically. Is there a scenario you'd like me to compare with other models?

million-dollar idea: whoever makes the highest bid within 15 seconds gets their prompt played in the next scene.

78.0K
601
33
18
1w ago
ailker
million-dollar idea: whoever makes the highest bid within 15 seconds gets their prompt played in the next scene.

Sam asks Frodo, 'Mr. Frodo, why don't we just take the Eagles straight to Mount Doom?' Frodo replies with a realization face, 'That actually makes sense.' Immediate cut to them riding giant Eagles, casually dropping the ring into the volcano. Sauron's tower instantly explodes. Giant white text overlays the screen: 'THE END'.

68.7K
340
10
4
7mo ago
ailker
Sam asks Frodo, 'Mr. Frodo, why don't we just take the Eagles straight to Mount Doom?' Frodo replies with a realization face, 'That actually makes sense.' Immediate cut to them riding giant Eagles, casually dropping the ring into the volcano. Sauron's tower instantly explodes. Giant white text overlays the screen: 'THE END'.
You can now choose the aspect ratio in nano-banana!
65.5K
889
40
36
11mo ago
ailker
You can now choose the aspect ratio in nano-banana!
I think H3 MAX can absolutely work as a rendering engine with the right prompting. I’ll share a post today showing how.
64.5K
682
25
66
2d ago
ailker
I think H3 MAX can absolutely work as a rendering engine with the right prompting. I’ll share a post today showing how.
I trained a flux-2 Klein 4B LoRA for this. It works much more stably and much faster than I expected. The cost per unit is $0.01, which is 15 times cheaper than the nano banana pro. It converts the inputs you enter into game assets and creates a simple spritesheet within a 2x2 grid. Just type ‘2x2 sprite sheet’ as the prompt. https://t.co/5Qwcyw1GvT
61.2K
687
21
44
7mo ago
ailker
I trained a flux-2 Klein 4B LoRA for this. It works much more stably and much faster than I expected. The cost per unit is $0.01, which is 15 times cheaper than the nano banana pro. It converts the inputs you enter into game assets and creates a simple spritesheet within a 2x2 grid. Just type ‘2x2 sprite sheet’ as the prompt. https://t.co/5Qwcyw1GvT
I might’ve found a way to make yesterday’s Blender to Real video ~5,000x faster (and better imo) lol. I put the scene together with GPT-6 Astra and PATINA in about 30 minutes. But it had around 7 million polygons, so rendering took a while. I split it into chunks across 8 GPUs and rendered it in about 30min. My estimate for an M4 Pro was around 40 hours. Obviously, I could’ve optimized the settings, but that’s for the version I posted yesterday. Since then, I’ve been trying different prompts to get H3 Max to follow the Blender animation while making the buildings and materials actually look real. I think I finally got it. The 30s video took about 30s to generate with H3 Max. Compared to that estimated 41h render, that’s roughly 5000x faster :) The part I’m most excited about is how much control this gives me. GPT-6 Astra can build a detailed 3D prototype in minutes, and I can use Blender to set up the camera and movement however I want, then have H3 Max follow it.
56.9K
710
34
48
4d ago
ailker
I might’ve found a way to make yesterday’s Blender to Real video ~5,000x faster (and better imo) lol. I put the scene together with GPT-6 Astra and PATINA in about 30 minutes. But it had around 7 million polygons, so rendering took a while. I split it into chunks across 8 GPUs and rendered it in about 30min. My estimate for an M4 Pro was around 40 hours. Obviously, I could’ve optimized the settings, but that’s for the version I posted yesterday. Since then, I’ve been trying different prompts to get H3 Max to follow the Blender animation while making the buildings and materials actually look real. I think I finally got it. The 30s video took about 30s to generate with H3 Max. Compared to that estimated 41h render, that’s roughly 5000x faster :) The part I’m most excited about is how much control this gives me. GPT-6 Astra can build a detailed 3D prototype in minutes, and I can use Blender to set up the camera and movement however I want, then have H3 Max follow it.

@eggheadrobby I've read the books, and my favorite series by far is LOTR. I know why this won't work. It's just a revival of an old, funny theory.

53.0K
465
18
1
7mo ago
ailker
@eggheadrobby I've read the books, and my favorite series by far is LOTR. I know why this won't work. It's just a revival of an old, funny theory.
Mark this day, nothing will ever be the same
52.7K
612
26
28
9mo ago
ailker
Mark this day, nothing will ever be the same
MEOWPOCALYPSE I’m honestly considering making a short film for this with Seedance 2.0 (even if I'm the only one who ever watches it)
49.2K
1.22K
73
210
6mo ago
ailker
MEOWPOCALYPSE I’m honestly considering making a short film for this with Seedance 2.0 (even if I'm the only one who ever watches it)

ilker (@ailker) X Stats & Analytics

ilker (@ailker) has 7.46K X followers with a 0.79% engagement rate over the past 12 months. Across 590 posts, ilker received 31.9K total likes and 4.29M impressions, averaging 54.1 likes per post. This page tracks ilker's performance metrics, top content, and engagement trends — updated daily.

ilker (@ailker) X Analytics FAQ

How many X (Twitter) followers does ilker have?+
ilker (@ailker) has 7.46K X (Twitter) followers as of September 2026.
What is ilker's X (Twitter) engagement rate?+
ilker's X (Twitter) engagement rate is 0.79% over the last 12 months, based on 590 posts.
How many likes does ilker get on X (Twitter)?+
ilker received 31.9K total likes across 590 posts in the last 12 months, averaging 54.1 likes per post.
How many X (Twitter) impressions does ilker get?+
ilker's X (Twitter) content generated 4.29M total impressions over the last 12 months.