rob - comfyui

854 posts

rob - comfyui banner
rob - comfyui

rob - comfyui

@hellorob

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

San Francisco, CA Katılım Şubat 2023
478 Takip Edilen5K Takipçiler
Sabitlenmiş Tweet
rob - comfyui
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 links.comfy.org/4dke0ki Create in App Mode. Share on ComfyHub. Learn more here: links.comfy.org/4bAOjuz

English
21
26
370
35.2K
rob - comfyui
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 👇

English
3
1
13
1.9K
rob - comfyui
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.
English
18
28
341
36.3K
rob - comfyui
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
English
0
0
2
400
Joe Sparks
Joe Sparks@joesparks·
@hellorob Super cool! I'm working on one that uses Qwen3
English
1
0
1
460
rob - comfyui
rob - comfyui@hellorob·
@bygregorr May have to do a head-to-head comparison with synclabs model to see if you're right...
English
0
0
0
538
Gregor
Gregor@bygregorr·
@hellorob wav2lip said hi from 2020. still undefeated for real talking head work.
English
2
0
0
604
Spectro 🇺🇸
Spectro 🇺🇸@Spectromachina·
@hellorob Even LTX 2.3 vanilla alone is able to produce some insane lip syncing results, now this is a step even further, thanks for sharing!
English
1
0
4
642
rob - comfyui
rob - comfyui@hellorob·
@comfystudiopro Waiting on our support for the new LTX node, but I will publish it to my ComfyHub profile asap
English
1
0
9
760
ComfyStudio Pro
ComfyStudio Pro@comfystudiopro·
@hellorob Hey @hellorob. Is this workflow included in ComfyUI's templates or is it available elsewhere? I'm building a short film workflow for my app and this would be extremely useful. I'm fighting to make this work.
ComfyStudio Pro tweet media
English
1
0
3
908
Ingi Erlingsson 🪄
Ingi Erlingsson 🪄@ingi_erlingsson·
More @ltx_model IC LoRA experimentation - I’m currently training a LoRA for seamless transitions. I think this one’s close to being ready to ship 🚚💨
English
29
12
223
14.9K
rob - comfyui
rob - comfyui@hellorob·
@TomLikesRobots Would love to check it out and see how to improve my workflow! x.com/hellorob/statu…
rob - comfyui@hellorob

Here's a SOTA Seedance 2.0 feature which I haven't seen anyone show off... Seamlessly extend videos using this ComfyUI workflow → Upload driving video → Prompt the next shots camera movement and scene action → Select the frame that most closely matches driving videos end frame → Workflow stitches audio and video Link to the workflow below!

English
1
1
4
814
TomLikesRobots🤖
TomLikesRobots🤖@TomLikesRobots·
30 second seamless videos in SeeDance 2. Annoyingly if you use SeeDance 2 to extend a video, you can get overlapping frames plus subtle brightness/contrast shifts at the join. I’ve been building SeeDance 2 Stitcher: it detects duplicate frames, trims the overlap, matches tone, and exports comparison previews. Quick demo below showing the middle 5 seconds of a 30 second stitched video. If anyone's interested, I can tidy this up, test it properly and share on Github.
TomLikesRobots🤖 tweet media
English
33
17
259
21.9K
rob - comfyui
rob - comfyui@hellorob·
Here's a SOTA Seedance 2.0 feature which I haven't seen anyone show off... Seamlessly extend videos using this ComfyUI workflow → Upload driving video → Prompt the next shots camera movement and scene action → Select the frame that most closely matches driving videos end frame → Workflow stitches audio and video Link to the workflow below!
English
4
5
54
6K
lucas gelfond
lucas gelfond@gucaslelfond·
the engineering team at A24 Labs is growing! we’re looking for excellent engineers excited about craft-driven products and the future of storytelling, comfortable wearing many hats to ship things and rolling up their sleeves with new technology. we’re a small, nimble team that works five days a week in midtown Manhattan + I love what I do! email me with a resume/site and something cool you’ve built lgelfond at a24films dot com if interested!
English
15
9
393
30.6K
DataVoid
DataVoid@DataPlusEngine·
I have just noticed quite litearlly 100% of the ComfyUI workflow websites are gone. OpenArt does not have it anymore, Comfy Workflows is gone, and esheep is gone,
English
18
4
72
16.2K

Keşfet

@AIWarper @PurzBeats @charliebcurran @infiniteyay @AmirMushich @joesparks @bygregorr @Spectromachina