Joined July 2010
- Tweets 1,041
- Following 576
- Followers 12,958
- Likes 4,703
324 Photos and videos
Pinned Tweet
Jan 13
Another example of using masking to add elements into a scene.
For this one, I used ComfyUI with Wan 2.2 Animate and masking to fill in the area where Wolverine’s mask would be.
For me, using AI in subtle, surgical ways is the key. It helps keep things more convincing instead of feeling overdone.
I know people will nitpick it, and that’s fine. I’m just excited to explore what feels like the future of VFX.
83
332
3,643
409,491
Jun 6
Mixing some vid2vid with some storyboard guidance.
Used Seedance 2.0, Premiere, ComfyUI, and NB2
23
26
289
14,140
Jun 4
Very cool effect by this legend. 🔥
locked n loaded🔒
Made in @comfyUI, @AdobeAE @Photoshop, @suno
Vid models: @Alibaba_Wan 2.2, @ltx_model 2.3 @thesystms FLW
Img models: @openai GPT 2.0, @googleai Nano Banana 2, @krea 2, @grok
GFX: @thesystms TimeSlice (see link below ⏬) GFX nodes, @meta Sam3 Sapiens2
1
1
21
1,761
Jun 3
A way to create quick previs shots to explore how a scene might look and play out before committing to a full production.
Generate a complete storyboard from a single prompt, then animate it in Seedance 2.0 using a reference image.
This ComfyUI workflow uses LLMs to expand prompts, create storyboard scenes, and format everything specifically for Seedance 2.0, making it easier to go from idea to animation with a more structured workflow.
To try this workflow, link below 👇
6
23
195
17,713
May 28
Press to Activate : The Boys Edition
Create transformation videos where a cube, sphere, capsule, or custom object transforms into a person or item with a button press using Seedance 2.0 inside ComfyUI.
The workflow automatically generates matching first and last frames while keeping the environment and style consistent throughout the effect.
Try the workflow, link below.
3
6
80
12,742
May 19
Testing out this LTX 2.3 LoRA for removing objects blocking a shot.
There’s still a bit of jitter when the face goes out of view, but coming from shooting weddings, I definitely would’ve tried using this to save shots when something was blocking my view.
6
34
392
23,210
Seedance 2.0 is great for changing environments, outfits, and the overall look of existing footage while preserving the original movement from the clip.
These examples were made in ComfyUI using prompts and reference images from a single source video.
Try this workflow, link below.
3
16
107
7,643
Real Human support for Seedance 2.0 is now available in ComfyUI. Unlock real human video generation with Seedance 2.0 now in ComfyUI.
This unlocks real-person video generation with consistent identity and authentic facial expressions — after a one-time verification.
10
34
301
48,432
Apr 20
Got to see @MedOumoumad demo some LTX 2.3 IC LoRAs at the ADOS event in Paris, so I had to try it myself.
If you want to test it out, I’ll drop the model Comfy workflow below.
14
31
244
39,142
Apr 20
6
1,316
A look at the video outpainting workflow in ComfyUI using LTX 2.3. 🎥
Instead of cropping your 16:9 footage for vertical, use this IC-LoRA setup to generate the missing space and keep your original frame.
Shout out to @MedOumoumad for their open source contribution. Link to workflow below! 👇
13
37
323
18,772
This viral “inflation effect” by @ingi_erlingsson gained significant traction across feeds.
Here’s how to recreate it in ComfyUI using a streamlined node-based workflow.
Click the link below for the full workflow ↓
13
27
270
24,093
Feb 27
A little late to the LTX-2 party, but finally tried it out.
Animated shape layers with keyframed warping in AE, then ran it through ComfyUI.
Love how fast it generates, and it’s especially solid if you want more precise, controlled movement like animating on beat.
9
32
358
20,286
Feb 19
I can’t wait for you all to use it inside of Comfy. 🚀
14
3
149
14,241
Feb 13
We’ve all seen this carpet.
We’ve all walked its roads. 🛣️
Some of us may have… stepped on a few buildings. 🏙️👟
9
1
45
5,338
Feb 11
With where AI is right now, it feels like the tinkering phase is starting to fade.
We’re not fully there yet, but generating impressive visuals isn’t the hard part anymore.
The hard part is what you do with them.
That’s where directing and writing begin to matter more.
As the barrier to beautiful visuals drops, the focus shifts,
from showcasing what the tool can do
to showcasing the idea behind it.
From “look what I made”
to “here’s what this means.”
When everyone has access to strong visuals, the advantage becomes taste, structure, pacing, story.
We’re not done experimenting.
But it’s time to roll up our sleeves and take storytelling seriously.
23
15
210
30,164