Iskarioto Dystopian retweeted
FLUX 3 Image Klein is here.
Open Weights with the quality of a large frontier model. Customizable and fast.
5.6B parameters and runs on a single consumer GPU.
Native 4K, bounding boxes, and pixel-perfect editing.
Iskarioto Dystopian retweeted
Introducing FLUX 3 Image.
Control every pixel.
Make precise multi-turn edits without changing any other pixel.
Lay out the image exactly how you want using bounding boxes.
Generate in up to 4K to preserve details.
Use up to 10 references to compose an image.
Commercial Weights available for companies running image generation at scale.
Open Weights version of FLUX 3 Image is launching in the coming weeks.
Iskarioto Dystopian retweeted
FLUX 3 Video now has fast, precise editing.
The fastest and lowest cost video editing model in the world.
In our internal benchmarking, it’s also ahead of other leading models in the accuracy and precision of edits.
Edit an existing video by:
• Adding, removing, or replacing objects and characters
• Replacing backgrounds
• Editing text
• Changing colors, materials, visual effects
• Changing or translating dialogue with accurate lip sync
• Changing the events of a clip
"AVERNUS-9" A space horror animated short film
Created with Flux 3 Text2video-audio
#Flux3 #AIanimation
Watch the full 8-minute version in 4k quality in the link below
"Reincarnation"
Short film created with Flux 3 Text2video-audio
Watch the full 6-minutes version in 4k quality here: youtu.be/ITlmSu_eax0
#flux3 #AIanimation
"Ghost Signal"
Music: Stable Audio 3 text2music
Video: Minimax H3 text2video
100% created with local open source models
#MinimaxH3 #StableAudio3 #ComfyUI
2
7
303
"Kinetic Abyss"
Music: Stable Audio 3 text2music
Video: LTX 2.3 text2video
100% created with local open source models
#StableAudio3 #LTX2 #ComfyUI
1
7
447
"System Override"
Music: Stable Audio 3 text2music
Video and SFX: LTX 2.3 text2video
100% created with local open source models
#StableAudio3 #LTX2 #ComfyUI
1
6
478
"Prototype"
Music: Stable Audio 3 text2music
Video: LTX 2.3 audioreactive text2video
100% created with local open source models
#StableAudio3 #LTX2 #ComfyUI
1
3
184
"Synchrotron"
Music: Stable Audio 3 text2music
Video: LTX 2.3 audioreactive text2video
100% created with local open source models
#StableAudio3 #LTX2 #ComfyUI
"Trauma" a dark and dramatic animated short film
Created locally using #Wan22 via #ComfyUI
4K quality here: youtu.be/mms1tLikH58
#AIVideo #AIFilm #AIArt #AIAnimation
6
347
"Psychotria Viridis"
Created with local Wan 2.2 via ComfyUI
youtu.be/63ZOmuiZlQ0
#AIVideo #AIFilm #AIArt #AIAnimation #wan22 #ComfyUI
"Necromancy" Local AI Animation
Generated with Wan 2.2 14b Text2video + Wan 2.2 creative upscale, via ComfyUI
youtu.be/zsjtLSh0xVQ
#AIVideo #AIFilm #AIArt #AIAnimation #wan22 #ComfyUI
"Blade Trance" Arca Gidan 2 entry
- Input images created with ZIT, and Wan 2.2 I2V as image editor
- Animated with Wan 2.2 I2V / FFLF, and Wan VACE Clip Joiner
- Upscaled with Wan 2.2 creative upscale
- Via ComfyUI
youtu.be/RkQVrGKNMO4
#AIAnimation #ZIT #wan22 #ComfyUI
"Neural Blackout"
An experiment using wan2.2 I2V as image editor to get the keyframes for using it with wan2.2 FFLF for consistent shots with unlimited length joining 3-second clips, using local open source AI models
4k quality: youtu.be/tA1RZNtJ6JI
#ZIT #wan22 #ComfyUI
Iskarioto Dystopian retweeted
The 2nd edition of The Arca Gidan Prize will begin this Sunday, now w/ a $50k prize fund!
Artists will be challenged to push open models to their limits from March 1, w/ winners receiving substantial prizes, travel to show their work at ADOS Paris + a 4.5kg Toblerone chocolate bar as their trophy.
This was funded using fees from the $dataclaw memecoin that the community created. While I don't own any of the coin, I received a percentage of the transaction fee on every trade, which I'm in turn giving to the prize fund for this competition!
- Theme + details announced: March 1
- Competition deadline: March 31
- Winners announced: April 2
- ADOS Paris: April 17-19
ADOS Paris is also supported by @Lightricks, and more competition supporters are very welcome!
Any additional fees will also go to the prize fund! Details on the coin below if you feel like gambling.
Links:
- Arca Gidan Website: arcagidan.com/
- Arca Gidan Discord: discord.com/invite/Yj7DRvckR…
- ADOS Paris Website: ados.events/
- My wallet - to validate all money goes to prizes: pump.fun/profile/3xDeFXgK1ni…
Someone created a coin for this & it's now worth $500k, w/ $15k fees due to me.
If the coin hits $1m MC, I'll sell the fees & give the money to the prize fund for The Arca Gidan Prize - Banodoco's open source AI art competition.
Same again at $10m, $100m & $1b. After this, I burn all fees. All the money goes to open source artists.
Here's the coin: Duxeg8HrG89Dq95oyiydrnFd8irZhjApGZu8PYrEpump
And PumpFun link: join.pump.fun/HSag/2fm2exv7
Here's The Arca Gidan Prize's website - next competition is announced March 1: arcagidan.com/
I won't tweet about it unless we hit milestones.




