ComfyUI node explorer • Sharing AI workflows • Diffusing pixels and conditioning latent space 🫡
San Francisco, CA
- Tweets 1,019
- Following 547
- Followers 6,359
- Likes 5,098
Pinned Tweet
Nodes have always been a huge hurdle for two groups: non-technical creatives wanting to try ComfyUI, and builders with complex workflows they can't easily hand off.
App Mode fixes both. Now you get the full power of node-based workflows without looking at a single node.
Here's a quick demo to show you how easy it is to go from nodes → app
Two massive updates for the ComfyUI ecosystem today:
1️⃣ App Mode: The power of the node graph, now behind an easy-to-use interface. Turn complex workflows into custom apps.
2️⃣ ComfyHub: A brand new home to discover, run, and share community workflows and apps instantly via URL. Try ComfyHub preview via links.comfy.org/4dke0ki
Create in App Mode. Share on ComfyHub.
Learn more here: links.comfy.org/4bAOjuz
22
23
391
41,509
Comfy API is live
Point it at a workflow JSON and it handles the rest:
→ Resolves your custom nodes, models, LoRAs, and Python deps
→ Pins it all, ComfyUI version included, into a versioned Build
→ Cuts an immutable release, so what you test is what ships
→ Deploys as an autoscaling endpoint on RTX PRO 6000, H100, H200, or B200
Click the link below to deploy your first workflow and learn more with our blog ⬇️
190
200
5,456
9,608,153
The Comfyverse is expanding
Comfy Router is live
One API for frontier image, video, 3D, and audio models.
Same model string. Same arguments. No new SDK, no new key, no redeploy.
What Comfy Router gives you:
→ Explicit routing. You name the provider, we call that provider. It's down? The request fails there. No silent fallback.
→ Every job returns the provider that ran it. Log it, bill it, debug it.
→ Async. submit() returns a request ID immediately. The queue retries 429s and transient errors until a slot opens. subscribe() submits and polls to completion.
→ Batch-friendly. Queue a few hundred jobs, hold the IDs, pull results as they land. Nothing blocking on a 5-min video render.
→ 24h retention on inputs and outputs, then deleted.
→ Comfy credits. No sub, no Router fee.
Providers at launch: Comfy. Runware, Wavespeed, Fal, Higgsfield. Multi-provider where the model supports it.
Get Your API Key with the link below. ⬇️
2
18
1,775
The best open source 3D AI generation model now runs natively in ComfyUI. The workflow runs 100% locally, on just 6GB of VRAM.
No more complex setup or dependency errors. TRELLIS.2 and Pixal3D work right out of the box, with one click.
Not to mention, it's FULLY COMMERCIAL-SAFE. The team re-implemented and removed every strictly-licensed library (thanks to the legend Kijai).
Drop in an image and click run, it's that easy to start. Go play with it.
Free workflow below!
40
135
1,277
74,234
Download the workflow to run on your machine, or try it on Comfy Cloud
comfy.org/workflows/920c795f…
1
4
47
5,680
To run locally, install Comfy Desktop here
comfy.org/download/
1
14
3,755
ComfyUI is the most used generative AI tool in the professional creative industry — used by teams at the largest studios in the world, like Netflix, Amazon, Nike, and more.
The barrier for non-technical creatives has always been the learning curve — python envs, model compatibility, debugging nodes, before you even touch a workflow. Now with Comfy MCP + agents, that barrier a lot lower.
Install Comfy Desktop + Comfy MCP, then just ask.
→ tell your agent your hardware and to install MiniMax H3
→ it grabs the right quantized models for your specs
→ helps you edit + build out workflows, while teaching you
→ have it develop custom nodes tailored to what you're building
If you understand the power of open source but the setup scared you off, this is your sign to try again.
Comfy MCP is now local and open-source!
The #1 ask after Comfy Cloud MCP shipped in June.
Your agent sees your actual install. So every node, custom nodes included, and every model on disk. It fetches files, starts your instance, gets a workflow to the point where it runs.
It is now the easiest way to help with your local Minimax H3 workflows!
Cloud MCP still does everything it did. Tell your agent where a job goes, or let it decide.
14
33
359
30,816
Big day for open source.
MiniMax Music 3 is undeniably a state of the art open weights Music Generation model and a real alternative to Suno.
My favorite part about open weights: the best is yet to come. Once the community starts playing with the model and training LoRAs, this model only gets better and allows for more control.
🎵MiniMax-Music3
Next-Generation Open-Weights Production-Ready & Versatile Music Model
huggingface.co/MiniMaxAI/Min…
82
232
2,906
322,888
MiniMax H3 is the SOTA open weight model... but the large model comes with slow gens (depending on your hardware). You can be waiting for minutes just for the generation to miss the mark
Here's a ComfyUI workflow to get the most out of H3 without the wait.
→ H3 Turbo LoRA (4–8 steps)
→ Model Preview Override + Tiny AutoEncoder H3 for a fast composition preview
→ Bad preview? stop it, tweak the prompt or seed
→ Save your precious gpu time
Workflow and model links below 👇
16
36
462
27,706
MiniMax H3 Turbo LoRA
huggingface.co/drbaph/MiniMa…
taeh3
huggingface.co/Kijai/MiniMax…
Workflow
pastebin.com/bEhLjUwi
1
1
36
2,329
It can run on a toaster.
Total memory footprint reduced by 66%. Live in ComfyUI!
MiniMax-H3 Is Now Publicly Available
huggingface.co/MiniMaxAI/Min…
5
2
68
4,680
Get your caffeine and GPUs ready.
Open source video models are taking a huge step forward tomorrow, thanks to Minimax H3. Truly a game changer for local users.
The cracked team at ComfyUI has optimized this huge model to the point where it can run comfortably on a toaster.
This generation was one shot and came out exactly how I imagined it. Used two reference images and an input audio that generated identically.
I can't wait to see what the community does with the open weights.
5
6
81
7,332
Open source video models are taking a huge step forward tomorrow, thanks to Minimax H3. Truly a game changer for local users.
The cracked team at ComfyUI has optimized this huge model to the point where it can run comfortably on a toaster.
This generation was one shot and came out exactly how I imagined it. Used two reference images and an input audio that generated identically.
I can't wait to see what the community does with the open weights.
23
14
307
30,354
Prompt: Bold comic-book ink style, heavy linework, red and blue-black palette, night city. Use <Picture 2> and <Picture 1> as reference frames and <Audio 1> exactly as it is.
CUT 1: top-down view of the little boy superhero on the rooftop — red cape fluttering in the wind, hands planted on his hips, freckles and a cocky grin as he looks straight up into the camera. The camera slowly descends toward him as he delivers his line — as he speaks, comic-book graphic overlay text word by word in sync with his voice: "GET READY TO" - "MEET" — "YOUR" — "MAKER" — huge jagged comic lettering, white with heavy black outlines and red drop shadows, tilted at scrappy angles, until the three words hang stacked in the air above him between his face and the lens.
TRANSITION: a whip pan off the rooftop that transitions the floating words away
CUT 2: low hero angle on the colossal black mech-kaiju towering over the skyline as it rears back and unleashes a terrifying roar — jaws wide with fangs, red eyes and chest-core flaring blinding bright, blue lightning arcing off its head, the roar's shockwave rippling dust and rattling windows down the buildings, comic-style speed-lines and ink splatter bursting from the impact of the sound. It leans into the camera as the roar peaks.
3
13
1,397
Hailou MiniMax H3 vs. Seedance 2.0 with 9 Reference images.
Only one model used all 9 images... and only one model generated a better output at 1/3 the cost...
8
6
134
13,811
Short form algorithms better get ready for FLUX 3.
"A timelapse video of a man in rugged worn clothing in a jungle clearing building a primitive stone portal from clay bricks and river metal, working with only a machete and bare hands. Full timelapse from digging the pit to the final stone — at which point a swirling purple portal ignites inside the ring, glowing and rippling, and he steps through it and vanishes. Continuous shot with no cuts, no music, no narration. Jungle sounds only, with a low hum as the portal opens."
Made with AI
6
4
60
4,689
Loving the native audio from this model
Introducing FLUX 3.
One multi-modal model for Image, Video, Audio and Action-Prediction. Creations are truer to life in every kind of style.
FLUX 3 Video is now available in early access (link below).
Jointly trained in one unified architecture, our model can be extended to predict actions for robotics. See our work with mimic and Audi in the thread.
3
5
99
7,307
Only one image model can pull off these one shot generations...
Identity transfer + 2 style LoRAs + perfect prompt adherence
And it's open source
2
1
31
3,362
Using the MCP and turning the convo into a reusable pipeline >>>
"Merch Printer" is the brand ad project I shared during the live stream about Comfy MCP last week.
This is a fully reusable pipeline. Drop the merch idea you have about Comfy and (if you wanna share your character image). I can print you into this video infinitely.
- I use Claude + Comfy MCP purely with our own brand reference (logo, color palette).
- I keep all the reference assets in the local folder for the agent to inspect, use, and organize.
- See all the assets generated during the ideation and experiments.
- Made in 4 hours in total (including waiting for generations and upscaling).
There's a new version of this post
1
5
508
The best part about open source is how it compounds.
Raw image model weights get open sourced → someone trains an outpainting LoRA on top → someone else wraps it for ComfyUI → I use it.
And the result is an outpainting workflow with Krea 2 that is super high quality + fast.
9
11
108
7,219
S/o @realrebelai for porting it over into Comfy. Check out the custom nodes
github.com/RealRebelAI/Comfy…
1
2
4
703