13 Photos and videos
PrismML retweeted
May 29
After @tcarambat’s video on our model — s/o for the support of local AI — we noticed the outputs looked much worse than expected on Macs.
Turns out it was a text encoder padding bug. Fixed now, and the improvement is huge! See the before/after results.
Please update your Bonsai Image pipeline to get the best outputs from your prompts!
May 28
Bug fix! Bonsai Image generations on local MacBook MLX will be even better quality.
Turns out how you pad text matters 😆 try it out! github.com/PrismML-Eng/Bonsa…
3
4
26
4,229
PrismML retweeted
May 28
Bug fix! Bonsai Image generations on local MacBook MLX will be even better quality.
Turns out how you pad text matters 😆 try it out! github.com/PrismML-Eng/Bonsa…
1
6
26
5,327
PrismML retweeted
May 27
First tests on my 12GB RTX 3060 with the new @PrismML Ternary Bonsai image 4B model are actually insane.
1408×704 in ~2.8s (4 steps),
peak VRAM under 7GB
extremely consistent
This might be the best text2image model you can run on small consumer cards rn.
Better benchmark is being done, will be sharing results soon.
Today we’re releasing 1-bit and Ternary Bonsai Image 4B.
A new family of image-generation models designed to run high-quality diffusion inference on local hardware: from laptops to phones.
5
11
50
9,779
PrismML retweeted
May 27
Local models are THIS GOOD already?
Today we’re releasing 1-bit and Ternary Bonsai Image 4B.
A new family of image-generation models designed to run high-quality diffusion inference on local hardware: from laptops to phones.
3
29
2,928
PrismML retweeted
May 26
A huge deal for the future of local AI
Today we’re releasing 1-bit and Ternary Bonsai Image 4B.
A new family of image-generation models designed to run high-quality diffusion inference on local hardware: from laptops to phones.
3
4
30
1,965
PrismML retweeted
May 26
Love everything PrismML's been doing for small local models!
You can generate images, on your tiny computer or browser 🔥
Today we’re releasing 1-bit and Ternary Bonsai Image 4B.
A new family of image-generation models designed to run high-quality diffusion inference on local hardware: from laptops to phones.
6
14
1,853
PrismML retweeted
May 26
running this locally on an iPhone is kinda crazy ngl!
big deal @PrismML
Today we’re releasing 1-bit and Ternary Bonsai Image 4B.
A new family of image-generation models designed to run high-quality diffusion inference on local hardware: from laptops to phones.
2
15
1,487
PrismML retweeted
May 26
On-device image generation on iPhone that is actually fast and also high quality!
Impressive model by @PrismML.
Today we’re releasing 1-bit and Ternary Bonsai Image 4B.
A new family of image-generation models designed to run high-quality diffusion inference on local hardware: from laptops to phones.
2
6
34
4,287
PrismML retweeted
May 26
Continuing my tests with Ternary Bonsai Image 4B. Same prompt with different seeds. Amazing work @PrismML!
6
18
1,647
PrismML retweeted
May 26
This is a huge leap forward for high quality diffusion inference on local hardware. I've had to spend 40GB to get similar quality in the past. The software optimizations happening are just as important as the hardware ones, if not more important. The future is bright!
Today we’re releasing 1-bit and Ternary Bonsai Image 4B.
A new family of image-generation models designed to run high-quality diffusion inference on local hardware: from laptops to phones.
2
3
20
1,519
PrismML retweeted
The age of Ternary Models has truly begun...
Today we’re releasing 1-bit and Ternary Bonsai Image 4B.
A new family of image-generation models designed to run high-quality diffusion inference on local hardware: from laptops to phones.
3
9
957
PrismML retweeted
May 26
~10 seconds for 1024x1024 using the Ternary model on M5 Max. WOW!
3
8
80
7,597
1-bit diffusion models are a thing now. It can run locally on your phone and create images within seconds.
At this pace, in a year or so, we'll get local video generation on consumer hardware.
Today we’re releasing 1-bit and Ternary Bonsai Image 4B.
A new family of image-generation models designed to run high-quality diffusion inference on local hardware: from laptops to phones.
3
4
21
1,919
PrismML retweeted
May 26
Testing the new bonsai model from @PrismML . I'm very impressed with this! Running 100% locally in my browser. huggingface.co/spaces/webml-…
2
3
24
1,667
PrismML retweeted
May 26
Really impressive, ~60 seconds for 1024x1024 using the Ternary model on my 17 Pro Max!
1
3
35
3,480
PrismML retweeted
Try the Bonsai Studio app on your iPhone: apps.apple.com/us/app/bonsai…
@PrismML 👏👏
We’re also launching Bonsai Studio, an iOS app for trying Bonsai Image 4B directly on your iPhone.
Run image generation on-device, with no subscription and no API requests.
2
5
12
3,809
PrismML retweeted
Diffusion models can be compressed too, quite aggressively, without losing the magic.
Intelligence Density is the metric: more capability per bit, per watt, per device.
At 1.21GB, PrismML’s ternary model keeps 95% of FLUX.2 Klein 4B accuracy while shrinking footprint 6.4x.
That means generation can move directly into the product experience on local devices: cheaper, faster, and private by default!
Congratulations to the @PrismML team.
Proud investor moment 👊
cc @khoslaventures
Today we’re releasing 1-bit and Ternary Bonsai Image 4B.
A new family of image-generation models designed to run high-quality diffusion inference on local hardware: from laptops to phones.
1
7
20
2,470
PrismML retweeted
May 26
WTF?! This changes image generation forever! 🤯 PrismML just released Binary and Ternary Bonsai Image 4B!
That's right, 1-bit diffusion models are here. Only ~3GB in size (FLUX.2 Klein 4B is 16GB).
The most shocking part? It can run 100% locally in your browser. Try it now! 👇
43
161
1,343
178,845
PrismML retweeted
May 26
1-Bit LLM > 1-Bit diffusion > 1-Bit ...?
Today we’re releasing 1-bit and Ternary Bonsai Image 4B.
A new family of image-generation models designed to run high-quality diffusion inference on local hardware: from laptops to phones.
5
4
33
3,827