ComfyUI (@ComfyUI) header
ComfyUI (@ComfyUI) profile picture

The most powerful open source workflow engine for visual AI https://xitter.gq/t.co/uKlvRQ6fW4

Joined June 2023
Higgsfield promised to open-source their entire platform. They didn’t. Let's help them. For the next two weeks, Comfy and our partners are putting up $25,000 in prizes for the best open-source builds on the Comfy Developer Platform. Partners: @NVIDIAAI, @runpod, @MiniMax_AI, @ltx_io, @bfl_ai → $10K grand prize → RTX 5090: Most Innovative → RTX 5090: Most Viral → RTX 5090: Open Weights Only → 10 runners-up: $250 in Comfy credits
218
395
158
4,961
679,800
ComfyUI retweeted
Genie 4 is now on @ComfyUI. Google DeepMind’s latest world model generates the world frame by frame, reacting to your inputs in real time: → Native audio generated with the scene → Physics like collisions and aerodynamics → Change the scene mid-session with a text prompt
4
6
2
26
1,563
Replying to @HeyGen
@HeyGen Decision 1 is now available in ComfyUI via Partner Nodes → Watches video, hears audio, reads images → Just type your question in plain language → Calibrated answers in ~100 ms → Moderation, identity checks, emotion and more
5
3
31
1,969
Links coming soon!
2
480
Feels good to prove them wrong 🤌
Last week you guys roasted my app. Then someone used it to fix a shot in a real car commercial 🧵
1
33
2,564
Kling Image 4.0 is now available in ComfyUI → Text to image → Image editing → Long Image: full webpages, product pages and app flows in a single generation → Generate up to 8k resolution images
7
6
2
102
7,262
Replying to @ideogram_ai
@ideogram_ai 4.6 is now available in ComfyUI → Native 4K output → Precise edits that change only what you ask for → Stronger character consistency → Exact color accuracy, down to brand hex codes → Masked edits for targeted changes
7
12
3
142
8,992
Links coming soon!
1
7
1,329
ComfyUI retweeted
“Just prompt it” is the “just Google it” of AI. Fine for amateurs. Useless when a client wants the same character in 40 shots, on brand, by Friday. Prompts get you outputs. Pipelines get you a job.
The studios that win with AI won’t have the best model. They’ll own their pipeline. We went through 450+ customer calls this year. The top reason teams pick @ComfyUI: control over every step. Only 22% asked for it. You don’t ask for what you already rely on. If you're using AI in production, do you own your pipeline or rent it?
4
38
3,015
ComfyUI retweeted
He had work to do, so he’s in today lol
After over a decade of waiting to play GTA 6…. I might be coming down with a bug, so I might be out tomorrow *cough* *cough* Cc @yoland_yan, @robinjhuang Made in @ComfyUI Credits: uekan2b ( IG )
2
2
9
1,688
After over a decade of waiting to play GTA 6…. I might be coming down with a bug, so I might be out tomorrow *cough* *cough* Cc @yoland_yan, @robinjhuang Made in @ComfyUI Credits: uekan2b ( IG )
2
1
13
3,897
Finally, all your models and custom nodes work on Comfy Cloud. We know that was the biggest limitation before for professional teams.
Your custom ComfyUI now runs in Comfy Cloud. Package your team’s nodes, models and LoRAs (private packs too) into one Build. Every artist opens the same setup in the browser, with nothing to install. What that means for production teams: → New artists start on the same setup as everyone else on day one → Roll out a new LoRA or update once, and the whole team gets it → Heavier workflows run on RTX PRO 6000, H100, H200 or the 180GB B200, with no hardware to buy → Concurrency scales up when clients need it and back down when the work is done → Developers run the same setup through the API Learn more and try your custom Comfy Cloud today with the link below ⬇️
5
5
1
63
3,724
ComfyUI retweeted
Almost every studio we work with has customized ComfyUI: their own nodes, their own LoRAs, private packs nobody outside the building has seen. That setup is their edge, and it was stuck on local machines. Now it runs in Comfy Cloud. Package it once, pick a GPU, and every artist has it in the browser.
Your custom ComfyUI now runs in Comfy Cloud. Package your team’s nodes, models and LoRAs (private packs too) into one Build. Every artist opens the same setup in the browser, with nothing to install. What that means for production teams: → New artists start on the same setup as everyone else on day one → Roll out a new LoRA or update once, and the whole team gets it → Heavier workflows run on RTX PRO 6000, H100, H200 or the 180GB B200, with no hardware to buy → Concurrency scales up when clients need it and back down when the work is done → Developers run the same setup through the API Learn more and try your custom Comfy Cloud today with the link below ⬇️
6
8
1
126
6,527
ComfyUI retweeted
The graph your production team builds in Comfy Cloud runs on the same Build you hit via API. Same nodes, same models, same pinned deps. No drift between what got approved and what ships. Package once from a workflow or Desktop snapshot → pick a GPU → deploy. Try your custom Comfy Cloud today ⬇️
Your custom ComfyUI now runs in Comfy Cloud. Package your team’s nodes, models and LoRAs (private packs too) into one Build. Every artist opens the same setup in the browser, with nothing to install. What that means for production teams: → New artists start on the same setup as everyone else on day one → Roll out a new LoRA or update once, and the whole team gets it → Heavier workflows run on RTX PRO 6000, H100, H200 or the 180GB B200, with no hardware to buy → Concurrency scales up when clients need it and back down when the work is done → Developers run the same setup through the API Learn more and try your custom Comfy Cloud today with the link below ⬇️
5
3
28
2,233
Your custom ComfyUI now runs in Comfy Cloud. Package your team’s nodes, models and LoRAs (private packs too) into one Build. Every artist opens the same setup in the browser, with nothing to install. What that means for production teams: → New artists start on the same setup as everyone else on day one → Roll out a new LoRA or update once, and the whole team gets it → Heavier workflows run on RTX PRO 6000, H100, H200 or the 180GB B200, with no hardware to buy → Concurrency scales up when clients need it and back down when the work is done → Developers run the same setup through the API Learn more and try your custom Comfy Cloud today with the link below ⬇️
13
20
17
172
26,146
ComfyUI retweeted
The studios that win with AI won’t have the best model. They’ll own their pipeline. We went through 450+ customer calls this year. The top reason teams pick @ComfyUI: control over every step. Only 22% asked for it. You don’t ask for what you already rely on. If you're using AI in production, do you own your pipeline or rent it?
7
4
1
63
6,674