@logtdx

dreaming of machines 💤

Joined October 2024
  • Tweets24
  • Following56
  • Followers596
9Media
logtd retweeted
Luma
@LumaLabsAIMar 23
Uni-1 is here! A new kind of model that thinks and generates pixels simultaneously. Less artificial. More intelligent.
450
760
689
4,746
6,513,853
logtd retweeted
Luma
@LumaLabsAIMar 5
Introducing Uni-1, Luma’s first unified understanding and generation model, our next step on the path towards unified general intelligence. lumalabs.ai/uni-1
Combine the black and white curly-haired dog with pink bandana, the Boston Terrier in plaid harness, and the black-and-white cat into a single scene where they are dressed in academic regalia, standing before a whiteboard filled with scientific diagrams and text, with the Luma AI logo placed in the top-left corner.

ALT Combine the black and white curly-haired dog with pink bandana, the Boston Terrier in plaid harness, and the black-and-white cat into a single scene where they are dressed in academic regalia, standing before a whiteboard filled with scientific diagrams and text, with the Luma AI logo placed in the top-left corner.

31
97
27
785
232,862
Stop guessing. Start directing. Ray3 Modify is now in Dream Machine. Edit and reimagine videos with all-new precise keyframe and character reference controls. Your vision, reimagined. Supercharge your production with rapid retouching, precise element swapping, and scene redesign.
24
76
31
405
133,673
Introducing Modify Video. Reimagine any video. Shoot it in post with director-grade control over style, character, and setting. Restyle expressive performances, swap entire worlds, or redesign the frame to your vision. Shoot once. Shape infinitely.
179
588
212
6,151
3,570,500
experimenting with regional prompting on the Hunyuan video model, giving some inception vibes left side prompt: cyberpunk & pan left right side prompt: steampunk & pan right
3
1
1
24
1,676
FlowEdit is an inversion-free method to edit images and videos. Releasing implementations of it for ComfyUI on a few models: * Flux -> github.com/logtd/ComfyUI-Flu… * LTXV -> github.com/logtd/ComfyUI-LTX… * Hunyuan -> github.com/logtd/ComfyUI-Hun… (WIP) Some examples below 🧵
13
61
11
386
38,016
more replies
LTX with STG can make some amazing changes to videos quickly github.com/logtd/ComfyUI-LTX…
1
3
1
28
2,909
And last but never least, Flux. FlowEdit really shines in that it can make precise edits while keeping the majority of the image intact (a bit more difficult to pull off in video though). github.com/logtd/ComfyUI-Flu…
1
13
1,255
Just published a set of ComfyUI nodes to use Genmo's Mochi to edit videos. github.com/logtd/ComfyUI-Moc… It uses rf-inversion, the gift that keeps on giving.
14
41
8
290
36,928
Been revisiting Reference-Only Control for Flux. It uses the diffusion model as a pseudo image encoder on a reference image to influence the generation. Results are somewhere between style and content transfer.
1
1
10
2,170
RAVE and FLATTEN were two of the papers that originally got me into diffusion models. They take inverse noise and apply consistency to image models. Now with RF-Inversion (thanks @litu_rout_ and @natanielruizg) I can try these on Flux. Not production quality, but still fun.
5
5
2
44
3,815
I'll be posting more of my implementations and experiments on here from now on For now, implementation of RF-Inversion for unsampling and editing images using Flux github.com/logtd/ComfyUI-Flu…
4
11
5
69
6,755
Load more