rob - comfyui

ComfyUI node explorer • Sharing AI workflows • Diffusing pixels and conditioning latent space 🫡

[rob - comfyui @hellorob]

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

[ComfyUI @ComfyUI]

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 https://t.co/kQxsxBs2bB

Create in App Mode. Share on ComfyHub.

Learn more here: https://t.co/s4oKA4Ab8f

[rob - comfyui @hellorob]

The best way to bring the composition from your head into an image → Ideogram V4 + drawing bounding boxes in Comfy.

The control here is quite unique. The model uses structured JSON so drawing bounding boxes to get the exact placement works very well.

The model only needs 12 steps (turbo), so iterating with different seeds + very impressive text rendering capability leads me to say this is a state of the art open source image model right now.

Using the 'Ideogram 4 Prompt Builder' node by Kijai.

[ComfyUI @ComfyUI]

The open source community has been delivering on LTX 2.3 LoRAs.

Fine tuning LTX 2.3 unlocks control that you can't get from closed models.

Here are 7 LoRAs that can save your footage.

There are too many incredible LoRAs to cover, so comment below your favorite that needs a showcase!

Links to all the workflows below 👇

[rob - comfyui @hellorob]

@ingi_erlingsson @ComfyUI @ltx_model @thesystms @Alibaba_Wan @Meta @OpenAI @suno @AdobeAE Really impressive button clicking to make this piece of art

[rob - comfyui @hellorob]

Try out the workflow!

https://t.co/LMbHBi91BA

[rob - comfyui @hellorob]

Testing VOID, Netflix's inpainting/object removal model.

For these POV shots, the real test was getting accurate masks with SAM3. With very simple prompts VOID handled the removal very well.

Using the default workflow on ComfyUI, 5 second video is ~110 seconds on an RTX PRO 6000.

[rob - comfyui @hellorob]

@SHL0MS @TransientLabs Dow servers are sus

https://t.co/uTpEUwLEAv

[rob - comfyui @hellorob]

It’s honestly really hard to believe what they’ve been hiding from us.

[rob - comfyui @hellorob]

Comparison of Omni, Seedance 2 and LTX 2.3 at video outpainting.

Surprisingly, Omni failed at this task (I tried a variety of reference videos and prompts). Might work better with realism…

Unsurprisingly, Seedance 2.0 nailed it and LTX did incredibly well at a fraction the cost.

Formal challenge to get video outpainting to consistently work with Omni

[rob - comfyui @hellorob]

@waitin4agi_ True. Also very impressive object removal + inpainting

[rob - comfyui @hellorob]

Search up "Pyramids of Egypt" and you'll see just how impressive the world knowledge is...

> a recording from a the back of a Camel in the outskirts of Cairo, a jerky zoom into something in the distance and then refocusing (with a bit of back and forth) (no timestamp or dialog)

[fofr @fofrAI]

Gemini Omni Flash:

> a recording from a capsule on the london eye, a jerky zoom into something in the distance and then refocusing (with a bit of back and forth) (no timestamp or dialog)

Note the world knowledge of London’s landscape, and the way the video is gently moving like the capsules do.

[rob - comfyui @hellorob]

@aidenguoai 🔥🔥🔥🔥

[rob - comfyui @hellorob]

@0xInk_ @ekello Keep cooking!!

[rob - comfyui @hellorob]

@hectorVFX Nice work! Which node is that for video comparing?

[rob - comfyui @hellorob]

Check it out here!
And s/o @AIWarper for the method and system prompt.

https://t.co/8fClbGQYGC

[rob - comfyui @hellorob]

Wrapped this technique into a simple ComfyUI workflow.

Upload a video + character image and watch the nodes work their magic.

You can also easily prompt for variation - in the vid below I prompted "extra emphasis on the rubberhose animated movement"

[A.I.Warper @AIWarper]

Below I will teach you how to reverse engineer any 15s video you see

You will need to tweak it a bit but I will explain in this thread exactly how to make these if you are ever curious

Thread below 👇

[rob - comfyui @hellorob]

@PurzBeats You forgot to ask it to tuck you into bed

[rob - comfyui @hellorob]

@charliebcurran hold up

[rob - comfyui @hellorob]

Save your credits and use open source models when you can.

The new LTX 2.3 lipdub LoRA paired with Chatterbox TTS voice cloning model is the best workflow for lip syncing, change my mind.

[rob - comfyui @hellorob]

@infiniteyay Okay i'm sold

[rob - comfyui @hellorob]

@AmirMushich Excited to see what you cook up!

[rob - comfyui @hellorob]

@joesparks Nice! I'll probably make another one with Qwen3 too. Chatterbox was giving pretty good results and it's insanely fast

[rob - comfyui @hellorob]

@bygregorr May have to do a head-to-head comparison with synclabs model to see if you're right...