akatz

@akatz_ai • 1,643 subscribers

AI Art Appreciator, Vibe Lifer and Codex Abuser. Building stuff.

Shorts

I ported DepthCrafter to ComfyUI! 🔥 Now you can generate super stable depthmap videos from any input video. The VRAM requirement is pretty high (>16GB) if you want to render long videos in high res (768p and up) It pairs well with Depthflow! Repo link in comments below👇

I ported DepthCrafter to ComfyUI! 🔥 Now you can generate super stable depthmap videos from any input video. The VRAM requirement is pretty high (>16GB) if you want to render long videos in high res (768p and up) It pairs well with Depthflow! Repo link in comments below👇

1,881,521 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

OK the Minimax H3 Person Remover V1 lora repo is live: I'm using it to generate better samples for the Character Swap V2 dataset. Training starting soon™️ Tomorrow I'm dropping an updated workflow for Character Swap that should help with videos longer than 5s. Lots more in the pipeline for y'all 🫡

OK the Minimax H3 Person Remover V1 lora repo is live: I'm using it to generate better samples for the Character Swap V2 dataset. Training starting soon™️ Tomorrow I'm dropping an updated workflow for Character Swap that should help with videos longer than 5s. Lots more in the pipeline for y'all 🫡

49,518 views • 6 days ago

OK so my Minimax H3 character swap LoRA has been trained to 1000 steps, and it's promising! It seems to hold the original video much more consistently than without the lora, including the original audio. However it falls short in a few ways: - Drifts from source in longer videos - Camera cuts turn into weird zooms or repositioning - Facial expressions don’t match well in close-ups I trained it on an RTX 4500 on Runpod overnight for around ~$11 but will need more VRAM for experimenting to get that 15s consistency. Also need to add more examples of videos with edits to have better edit-matching... and more expression-matching examples.... I've posted lora and dataset on huggingface for y'all either way: If anyone wants to throw me some X bucks or lend me their GPU I'll train it on a RTX 6000 Pro next 😁

OK so my Minimax H3 character swap LoRA has been trained to 1000 steps, and it's promising! It seems to hold the original video much more consistently than without the lora, including the original audio. However it falls short in a few ways: - Drifts from source in longer videos - Camera cuts turn into weird zooms or repositioning - Facial expressions don’t match well in close-ups I trained it on an RTX 4500 on Runpod overnight for around ~$11 but will need more VRAM for experimenting to get that 15s consistency. Also need to add more examples of videos with edits to have better edit-matching... and more expression-matching examples.... I've posted lora and dataset on huggingface for y'all either way: If anyone wants to throw me some X bucks or lend me their GPU I'll train it on a RTX 6000 Pro next 😁

35,350 views • 18 days ago

H3 is kind of insane, I generated this video in 26m 6.7s on my 4090 machine Used LTX 2.5 to upscale the initial 480p H3 video + RIFE interpolation Can you tell where I just got back from on vacation? 😅

H3 is kind of insane, I generated this video in 26m 6.7s on my 4090 machine Used LTX 2.5 to upscale the initial 480p H3 video + RIFE interpolation Can you tell where I just got back from on vacation? 😅

31,663 views • 1 month ago

No more content to load