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

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

Joined June 2023
Photo by ComfyUI (@ComfyUI)Photo by ComfyUI (@ComfyUI)Photo by ComfyUI (@ComfyUI)Photo by ComfyUI (@ComfyUI)Photo by ComfyUI (@ComfyUI)Photo by ComfyUI (@ComfyUI)Photo by ComfyUI (@ComfyUI)Photo by ComfyUI (@ComfyUI)Photo by ComfyUI (@ComfyUI)Photo by ComfyUI (@ComfyUI)
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
219
396
157
4,958
676,683
Replying to @bria_ai_
@bria_ai_ RMBG 3.0 is now in ComfyUI via Partner Nodes. → Cleaner cutouts on hair, fur and motion blur → True 8-bit alpha matte, not a hard mask → Same image, same result, every time → Trained only on licensed dataSelect RMBG3 in the Bria Remove Image Background node.
2
4
1
42
1,561
Links coming soon!
1
1
353
I'm yet to find a limit to what's possible with custom nodes in @ComfyUI.. I'm working on a group of nodes that pull frames from a clip, give it to an LLM that describes what it sees and hands it to another set of nodes that animate + track the type onto the clip. Super fun!
🤖 Made with AI
6
4
99
5,108
ComfyUI retweeted
The best things are created when builders have the freedom to create, share, and build on each other’s ideas in the open. Stay Comfy! 🤝
As we close out the #OpenSourceHiggsfield challenge, we’re still smiling. We knew you’d all  build amazing things. What we enjoyed even more was watching a community find each other. We loved seeing people who’d never met team up across time zones. We loved watching the Discord light up during build nights, with everyone sharing progress, asking questions, and hyping each other’s work. That’s the part we’ll remember. You weren’t just building tools, you were building them together, in the open, for anyone to use. It reemphasizes to us that creativity should be built in the open. Thank you for being apart of it. And we’re not done. The next challenge is coming soon, and we can’t wait to build with you again. If we win, we all win! 🤝
4
3
1
36
5,832
The best things are created when builders have the freedom to create, share, and build on each other’s ideas in the open. Stay Comfy! 🤝
As we close out the #OpenSourceHiggsfield challenge, we’re still smiling. We knew you’d all  build amazing things. What we enjoyed even more was watching a community find each other. We loved seeing people who’d never met team up across time zones. We loved watching the Discord light up during build nights, with everyone sharing progress, asking questions, and hyping each other’s work. That’s the part we’ll remember. You weren’t just building tools, you were building them together, in the open, for anyone to use. It reemphasizes to us that creativity should be built in the open. Thank you for being apart of it. And we’re not done. The next challenge is coming soon, and we can’t wait to build with you again. If we win, we all win! 🤝
4
3
1
36
5,832
ComfyUI retweeted
As we close out the #OpenSourceHiggsfield challenge, we’re still smiling. We knew you’d all  build amazing things. What we enjoyed even more was watching a community find each other. We loved seeing people who’d never met team up across time zones. We loved watching the Discord light up during build nights, with everyone sharing progress, asking questions, and hyping each other’s work. That’s the part we’ll remember. You weren’t just building tools, you were building them together, in the open, for anyone to use. It reemphasizes to us that creativity should be built in the open. Thank you for being apart of it. And we’re not done. The next challenge is coming soon, and we can’t wait to build with you again. If we win, we all win! 🤝
6
4
2
63
8,576
A museum painting, but the camera doesn’t stop at the frame. This workflow pushes the shot straight into the artwork and turns the painting into a full 3D space you can move through. A great way to create depth, transitions, and that surreal “step inside the image” effect. Prompt + workflow below 👇
16
26
6
392
22,165
We’re bringing @StabilityAI's Image Services and 3D APIs to Comfy. ComfyUI grew up alongside Stable Diffusion, and Stability AI’s models have been part of this community from the beginning. This makes it easier to keep building with them alongside the other models you use. Click the link below to learn more.
8
10
4
115
9,826
🤝🤝
Meet the team behind MOSS-Image. The @ComfyUI -Org/MOSS-Image repo on Hugging Face is over 6.3M downloads in the past month. See what the model they trained can do. 👇 nitter.cf/ting_/status/212081531…
1
3
71
6,010
ComfyUI retweeted
Running an LLM for prompt enhancement alongside a diffusion model is a heavy lift for consumer GPUs. Comfy engineer @Rattus128 used multi-token prediction to help double LLM token rates in ComfyUI New in v0.45. Read his blog post ⬇️
6
10
2
113
7,291
Built in the open. Learned in the open. Hired for in the open. Open Source Will Win! 🤝
If you're a creative wondering what to learn in 2027, you need to read this. Adobe MAX is this week. One of their AI Studio roles asks for "hands-on proficiency with @ComfyUI , including custom node development." The biggest name in subscription creative software is hiring for an open-source tool. It's not the "alternative" anymore. It's the skill people are screening for. And it's not just Adobe. We're seeing an influx of "ComfyUI Artist" and creative technologist roles show up at VFX shops and brand studios almost every week. For 20 years, creative skills lived inside someone else's subscription. Open source flips that. Learn it once, and it goes with you to the next endeavor. Nobody can reprice what you know. Learn the thing you get to keep.
9
8
2
104
8,181
What do AI video models like Seedance 2.5 and MiniMax H3 pick up from a 3D blockout? We break it down with examples, from basic shapes to fully animated character. Follow for more AI video tips and breakdowns.
28
24
6
387
20,888