Banodoco (@banodoco) profile picture

Banodoco

@banodoco

Working to help the open AI art ecosystem thrive. Amplifying posts from our Discord. Join us: https://nitter.cf/t.co/Zm17NaEDWT

 2nd Renaissance (2085 - ????)
banodoco.ai
Joined February 2023
  • Tweets846
  • Following0
  • Followers4.3K
Open-sourcing Banodoco Hivemind, a live dataset of 1M+ Discord messages featuring talented artists/engineers discussing open image and video models. Designed as an agent-driven skill to equip your agent with the tacit knowledge it needs to push open models to their limits.
7
7
4
67
11,023
“Say, what’s the best Minimax H3 fine-tune and distillation?” (generation by Kijai)
1
1
7
555
I'm glad to announce that I've finally finished the Minimax H3 version of my crossview-warp model finetune. For those who don't know what it is, it's a model that lets you regenerate your existing video clip from a new camera angle or with a new camera movement. Link to model👇
13
23
4
270
46,040
Yue2 allows for custom voice training on a production-class music model for the first time. Sample by gueykhalamari trained w/ AI-Toolkit using Samuel L. Jackson’s voice, link below.
5
4
1
114
5,738
Latent mask inpainting with H3 enables highly divergent changes while holding consistency. Examples by PhoenixRisen + AbleJones - workflow below.
3
13
2
159
10,974
You can find the workflow by AbleJones in the minimax_h3_resources channel here: discord.gg/dstjQYQNt
Discord - Group Chat That’s All Fun & Games

Discord - Group Chat That’s All Fun & Games

Discord is great for playing games and chilling with friends, or even building a worldwide community. Customize your own space to talk, play, and hang out.

discord.com
7
788
Seamless video/audio continuations in MiniMax H3 via latent masking, demo'd by AbleJones:
10
14
2
174
11,706
You can find a similar workflow here: github.com/seitanism/ComfyUI…
8
668
CrossViewWarp allows you to change the camera arc of an existing video while maintaining the motion. Demonstration w/ LTX2.5 by @ChetiArt, link below.
7
25
1
287
16,829
Link: huggingface.co/Cseti/LTX2.3-…
Cseti/LTX2.3-22B_IC-LoRA-CrossView-Warp · Hugging Face

Cseti/LTX2.3-22B_IC-LoRA-CrossView-Warp · Hugging Face

Machine learning model. Download, explore files and run it on Hugging Face.

huggingface.co
12
797
seitanism injecting frames into specific positions with h3 - see how it handles 1 frame every 1 second:
2
4
2
72
6,681
(gen by orabazes)
2
13
1
141
6,676
Wan Animate 2 allows for highly versatile motion transfer in a wide variety of styles. Examples by Kijai:
2
20
1
167
9,044
On out-of-distribution requests, H3 can produce highly coherent visuals and audio - example by @nebsh83:
1
1
42
2,424
How your 6 y/o potato GPU reacts when you try to run Minimax (gen'd by _kruss_)
Banodoco (@banodoco) profile pictureBanodoco@banodocoAug 5
76 five-second clips exploring different animation styles with MiniMax H3. All generated locally on a six-year-old GPU by the_shadow_nyc:
2
5
1
49
5,328
Inpainting based on a reference w/ Minimax H3. Examples by AbleJones, feat. @PurzBeats:
20
54
5
730
41,615
76 five-second clips exploring different animation styles with MiniMax H3. All generated locally on a six-year-old GPU by the_shadow_nyc:
14
38
6
506
32,025
The next generation of vid2vid will go to some magnificent, disturbing places (generated locally by Dawnll using Minimax M3)
6
24
4
390
26,893
Historically, the lag between a frontier video model launching and a broadly comparable open-weight model running locally has averaged roughly nine months. If that trend holds, we should expect a Seedance 2-level local model sometime between August and December this year.
Image from Banodoco (@banodoco)
4
2
1
23
5,794
Load more