Zeke Sikelianos
@ziki.boo
Aging Twitter user from 2007, back when it was a service where you texted messages to 40404 and they blasted to all your followers. Now scared of Elon and X, and optimistic about this AT PROTOCOL thing.
@LeonardoAi_ hitting a TOS bug at signup on iOS…
February 23, 2025 at 11:04 AM
@LeonardoAi_ hitting a TOS bug at signup on iOS…
You know what's great? Documentation.
You know what's even better? Not having to read it.
Here's me feeding https://cog.run/llms.txt into @cursor_ai chat to help me create a @replicate model:
You know what's even better? Not having to read it.
Here's me feeding https://cog.run/llms.txt into @cursor_ai chat to help me create a @replicate model:
February 23, 2025 at 11:09 AM
You know what's great? Documentation.
You know what's even better? Not having to read it.
Here's me feeding https://cog.run/llms.txt into @cursor_ai chat to help me create a @replicate model:
You know what's even better? Not having to read it.
Here's me feeding https://cog.run/llms.txt into @cursor_ai chat to help me create a @replicate model:
Okay the 70B @ollama version brought my fancy new macbook to a crawl, and this is all the output it's generated so far after 10+ minutes running:
February 23, 2025 at 11:09 AM
Okay the 70B @ollama version brought my fancy new macbook to a crawl, and this is all the output it's generated so far after 10+ minutes running:
Having trouble getting the dog to flip the table.
February 23, 2025 at 11:09 AM
Having trouble getting the dog to flip the table.
The `all-the-public-replicate-models` npm package now has daily run counts for all the public models on @replicate.
Somebody build a leaderboard! (Looking at you, @aimodelsfyi)
Somebody build a leaderboard! (Looking at you, @aimodelsfyi)
February 23, 2025 at 11:09 AM
The `all-the-public-replicate-models` npm package now has daily run counts for all the public models on @replicate.
Somebody build a leaderboard! (Looking at you, @aimodelsfyi)
Somebody build a leaderboard! (Looking at you, @aimodelsfyi)
@ellipsis_dev nice to meet you :)
February 23, 2025 at 11:09 AM
@ellipsis_dev nice to meet you :)
The @LumaLabsAI "ray" model on @replicate (aka Dream Machine) lets you generate video using a text prompt, a starting frame, and an ending frame.
Pretty wild.
Pretty wild.
February 23, 2025 at 11:10 AM
The @LumaLabsAI "ray" model on @replicate (aka Dream Machine) lets you generate video using a text prompt, a starting frame, and an ending frame.
Pretty wild.
Pretty wild.
The @replicate playground supports video models!
1. Generate an image (e.g. with your Flux fine-tune)
2. Use it as a starting frame for a video
3. Kick off several generations at once
4. Kick back and enjoy the show
Links in next post...
1. Generate an image (e.g. with your Flux fine-tune)
2. Use it as a starting frame for a video
3. Kick off several generations at once
4. Kick back and enjoy the show
Links in next post...
February 23, 2025 at 11:10 AM
The @replicate playground supports video models!
1. Generate an image (e.g. with your Flux fine-tune)
2. Use it as a starting frame for a video
3. Kick off several generations at once
4. Kick back and enjoy the show
Links in next post...
1. Generate an image (e.g. with your Flux fine-tune)
2. Use it as a starting frame for a video
3. Kick off several generations at once
4. Kick back and enjoy the show
Links in next post...
Are you using @replicate's API to generate images?
If you wanna keep those images for longer than an hour, you'll need to store them yourself. @cloudfare workers are a perfect fit for that.
I wrote a guide to get you going. 🧵
If you wanna keep those images for longer than an hour, you'll need to store them yourself. @cloudfare workers are a perfect fit for that.
I wrote a guide to get you going. 🧵
February 23, 2025 at 11:10 AM
Are you using @replicate's API to generate images?
If you wanna keep those images for longer than an hour, you'll need to store them yourself. @cloudfare workers are a perfect fit for that.
I wrote a guide to get you going. 🧵
If you wanna keep those images for longer than an hour, you'll need to store them yourself. @cloudfare workers are a perfect fit for that.
I wrote a guide to get you going. 🧵
It's pretty great for tweaking inputs until you get things just right. It supports image generation models like Flux, SD3.5, Ideogram v2, Recraft v3, and even Flux and SDXL fine-tunes.
Try it out at https://replicate.com/playground
Try it out at https://replicate.com/playground
February 23, 2025 at 11:20 AM
It's pretty great for tweaking inputs until you get things just right. It supports image generation models like Flux, SD3.5, Ideogram v2, Recraft v3, and even Flux and SDXL fine-tunes.
Try it out at https://replicate.com/playground
Try it out at https://replicate.com/playground
In case you missed it, @replicate now has a web playground where you can hit Enter a bunch of times.
February 23, 2025 at 11:15 AM
In case you missed it, @replicate now has a web playground where you can hit Enter a bunch of times.
@Calendly feature request: Please don't add this query param onto the URL if it's not needed. I don't want to have to do surgery on the URL every time I want to share it with someone.
February 23, 2025 at 11:15 AM
@Calendly feature request: Please don't add this query param onto the URL if it's not needed. I don't want to have to do surgery on the URL every time I want to share it with someone.
A little late, but I'm brainstorming costume ideas.
February 23, 2025 at 11:20 AM
A little late, but I'm brainstorming costume ideas.
Media Provenance is a new project I quietly created a month ago as an experiment.
When I encounter AI-generated media like images, audio, and video, I want to know where it came from. What AI model was used to create it? What were the inputs to the model?
Media Provenance is a
When I encounter AI-generated media like images, audio, and video, I want to know where it came from. What AI model was used to create it? What were the inputs to the model?
Media Provenance is a
February 23, 2025 at 11:20 AM
Media Provenance is a new project I quietly created a month ago as an experiment.
When I encounter AI-generated media like images, audio, and video, I want to know where it came from. What AI model was used to create it? What were the inputs to the model?
Media Provenance is a
When I encounter AI-generated media like images, audio, and video, I want to know where it came from. What AI model was used to create it? What were the inputs to the model?
Media Provenance is a
Yo there's a new AI model that can generate SVG images. 🤯
Been waiting years for this... 🧵
Been waiting years for this... 🧵
February 23, 2025 at 11:21 AM
Yo there's a new AI model that can generate SVG images. 🤯
Been waiting years for this... 🧵
Been waiting years for this... 🧵
Hey look I'm non-consensually famous. 🧐
February 23, 2025 at 11:21 AM
Hey look I'm non-consensually famous. 🧐
@loom please let me hit escape during the 3...2...1 countdown to abort starting the recording.
I sometimes hit the global keyboard shortcut by accident and have no recourse. In the interim I'm just disabling all the shortcuts.
I sometimes hit the global keyboard shortcut by accident and have no recourse. In the interim I'm just disabling all the shortcuts.
February 23, 2025 at 11:21 AM
@loom please let me hit escape during the 3...2...1 countdown to abort starting the recording.
I sometimes hit the global keyboard shortcut by accident and have no recourse. In the interim I'm just disabling all the shortcuts.
I sometimes hit the global keyboard shortcut by accident and have no recourse. In the interim I'm just disabling all the shortcuts.
; @ValDotTown is very cool, but their new Townie AI feature takes it to the next level.
I used Townie to set up a little click-tracking analytics redirect endpoint thingy in like... 30 seconds?
I used Townie to set up a little click-tracking analytics redirect endpoint thingy in like... 30 seconds?
February 23, 2025 at 11:26 AM
; @ValDotTown is very cool, but their new Townie AI feature takes it to the next level.
I used Townie to set up a little click-tracking analytics redirect endpoint thingy in like... 30 seconds?
I used Townie to set up a little click-tracking analytics redirect endpoint thingy in like... 30 seconds?
Don't know how to wink?
AI is here to help.
AI is here to help.
February 23, 2025 at 11:26 AM
Don't know how to wink?
AI is here to help.
AI is here to help.
I'm really happy that we've started implementing new pricing structures at @replicate, like price-per-output instead of price-per-second.
Per-second pricing is tough: We continually made Stable Diffusion models faster for our users, but every time we did so it cut into our
Per-second pricing is tough: We continually made Stable Diffusion models faster for our users, but every time we did so it cut into our
February 23, 2025 at 11:31 AM
I'm really happy that we've started implementing new pricing structures at @replicate, like price-per-output instead of price-per-second.
Per-second pricing is tough: We continually made Stable Diffusion models faster for our users, but every time we did so it cut into our
Per-second pricing is tough: We continually made Stable Diffusion models faster for our users, but every time we did so it cut into our