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.
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
Just published a set of ComfyUI nodes to use Genmo's Mochi to edit videos. github.com/logtd/ComfyUI-… It uses rf-inversion, the gift that keeps on giving.
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.
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.
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-…
United States Trends
- 1. Jets 80.1K posts
- 2. Jets 80.1K posts
- 3. Justin Fields 8,426 posts
- 4. Aaron Glenn 4,366 posts
- 5. Sean Payton 2,068 posts
- 6. London 202K posts
- 7. #HardRockBet 3,354 posts
- 8. Bo Nix 3,374 posts
- 9. Garrett Wilson 3,284 posts
- 10. HAPPY BIRTHDAY JIMIN 149K posts
- 11. Tyrod 1,582 posts
- 12. #OurMuseJimin 194K posts
- 13. #DENvsNYJ 2,118 posts
- 14. #JetUp 1,934 posts
- 15. Peart 1,899 posts
- 16. #30YearsofLove 171K posts
- 17. Bam Knight N/A
- 18. Kurt Warner N/A
- 19. Rich Eisen N/A
- 20. Sutton 2,758 posts
Something went wrong.
Something went wrong.