This ComfyUI workflow lets you draw lines and annotations to guide motion, define where actions should happen, and influence movement throughout a scene.
An integrated LLM translates those annotations into prompt instructions, making it easier to direct motion visually instead of relying entirely on text prompts.
The workflow works best with clear, intentional paths, while more complex routes with frequent direction changes can be harder to follow consistently.
To try this workflow, link below 👇
krea discord challenges are weekly now ⚡
week 1: fictional objects — design something that doesn't exist. weapons, gadgets, vehicles, artifacts. make it real (or beautifully unreal).
win the week, get a prize
link below ⬇️
Finally. It wasn't always that way in Canada!!! It took a brave man who wanted to win to take on the system and put in place the best players & overnight 1/2 the team was Black. Then all of a sudden we have quality. We've always had it. Time for change.
Jesse Marsch spoke this week about how special it is that #CanMNT reflects Canada's multiculturalism, and his comments caught the attention of Dutch great Ruud Gullit 🍁 #FIFAWorldCup
https://t.co/sgUOeO8JGq
Jesse Marsch spoke this week about how special it is that #CanMNT reflects Canada's multiculturalism, and his comments caught the attention of Dutch great Ruud Gullit 🍁 #FIFAWorldCup
https://t.co/sgUOeO8JGq
Turn natural language prompt to Ideogram bbox prompt.
No more messing around with bbox creation, let LLM do it for you, completely local (llamacpp + Qwen)
Was talking to @jconorgrogan and we both wanted something like this but he ran out of LLM credit so I asked Fable instead.
Anthropic engineer:
"You're not supposed to prompt Claude. You're supposed to build a system that prompts itself."
this is one of the best workflows I've seen in a long time
in this video she breaks down exactly how most people are using Claude:
- the daily workflows Anthropic's own engineers automated first
- the task pipelines most users don't know Cowork can run
- the scheduling system that handles your busywork while you do real work
- why opening Claude to type one prompt at a time is the 2024 way of doing things
if you've been using Claude for more than a month and never left the chat window, you've been using one agent when you could be running a team of them
instead of another show tonight, watch this
make sure to bookmark it before it gets lost in your feed
the guide is in the article below
@GLOBALCENTER14@TeamYouTube Automation has gone too far. This content is awesome and is needed. This is what we are supposed to see on youtube that will eventually challenge Hollywood. Reinstate this channel and content. Do not de-monotize
I'm a solo filmmaker. I create cinematic AI films up to 1:30h long — original scripts, shot-by-shot direction, original music composed for every scene. Each film takes weeks to produce.
In four languages, my audience has cried, debated characters, written theories, and begged for sequels. Netflix producers and Hollywood professionals contacted me after watching my work.
One week ago, YouTube's automated system demonetized all my channels for "inauthentic content." The appeal was rejected in hours. No human review. No explanation.
This is my work:
🎬 https://t.co/TVIEhaXfVi 🎬 https://t.co/qTTafzPZLq 🎬 https://t.co/9tP86oAsfH 🎬 https://t.co/tGXyaEI92e
Watch 10 seconds of any video. Read the comments. Then tell me this is inauthentic.
@TeamYouTube I need a human review. My community is here to back that request.
#SaveButacaSalvaje2 #quantumrecap #poltronaselvagem #cinéflash
We just raised $30M at a $500M valuation, bringing our total funding to $47M.
Led by @craft_ventures , with @PaceCap , @chemistry , TruArrow, and others.
But before anything else: this belongs to the community.
ComfyUI started as one developer and one open-source repo. No roadmap. No company. Just creators who wanted real control over how they built with AI.
That community is now:
→ 4 million users
→ 60,000+ community-built nodes
→ 150,000+ daily downloads
Every number traces back to people who built in the open, for anyone to use.
Here's where the funding goes:
→ Comfy Cloud: for teams and studios that need security and scale
→ Collaborative workflows: versioning and iteration built for how studios actually work
→ A better local experience: more seamless, more stable
→ Ecosystem reliability: making 60,000+ community nodes more dependable
→ Day-one model support: every major release, compatible at launch
We are not building a walled garden.
We are building open infrastructure, built to last.
Thank you genuinely,
The ComfyUI Team
If Meta is going to abandon the Llama brand, they might as well release the trademark to the public domain too.
Let tools like llama.cpp live on freely as their own brand.
Let "Llama" live on as the mascot for open weights, because that's exactly what it was.
First frame + Last frame = Fashion ads in minutes.
Here’s how I generated this U.S. Polo sequence using Kling 3.0 + Calico AI:
→ The Input: A start frame and an end frame to lock in the subject and composition.
→ The Prompt: Don't just ask for a "cool video." Specifically prompted for "slow cinematic push-in," "shallow depth of field," and "micro-parallax" to get that premium brand-film look.
→ The Output: Motion that looks like a high-budget fashion shoot.
Studio shoots are expensive, but AI is leveling the playing field.
Comment 'PROMPT' if you want me to send you all of the prompts and the system I used to build this.
(must be following so I can dm you!)
ChatGPT + laptop + internet connection + 60 minutes per day = $9500 every month.
I normally sell this guide for $81, but for the next 48 hours, it’s yours 100% FREE.
To get: -
1. Follow me (So I can DM you )
2. Retweet
3. Reply " Ai "
Must follow me to get DM. Free for 48 hours
This is how top ads are being made now.
I made a simple cheat sheet to create hyper-realistic AI videos for ads.
Like, RT & comment “Video” — I’ll share it.
(must be following)