David Soeiro

Anciennement Consultant Digital Senior Freelance, je parle principalement de IA, nouvelles technologies et autres Geekeries...

[David Soeiro @David_Soeiro]

Added 8K FULLDOME (8192 x 8192 px) versions to my @DeviantArt -> https://t.co/nELvGP9ztl #AI #IA @Google @GeminiApp @upscayl @Affinity

[David Soeiro @David_Soeiro]

Generating portrait pictures with @Google @GeminiApp (~400Ko), upscaling them with @upscayl to x13 (26624 x 26624 px, ~400Mo😓) to edite them with @Affinity Photo 💪 before downscale them to 8K FULLDOME, result into a winning combo 🥰 Every Affinity Photo file is more than 2Go 🥶

[David Soeiro @David_Soeiro]

@ComfyUI If anyone else is experiencing the same problem as me, the solution is here (remove reserved VRAM before updating) ->

[David Soeiro @David_Soeiro]

@ComfyUI Hi, the latest version of ComfyUI 0.9.2 Desktop is not working, according to Gemini's analysis, there is this problem.

[Affinity @Affinity]

Design, edit, animate. @cavalry__app is now completely free with your Canva account 🎉 Motion has become a core part of modern brand work, and now you've got photo editing, vector design, layout, and 2D animation all under one roof with one login.

[David Soeiro @David_Soeiro]

IA is going more impressive everyday...

[YouArt @YouArtStudio]

Seedance 2.0 early access still open, and we can't wait to see more of your excellent creations!

Completing the following two steps and unlock the access:

- Follow us
- Fill the form below
https://t.co/3zcwO03I9U

We’re waiting for your crazy ideas!

#Seedance2 #YouArt

[David Soeiro @David_Soeiro]

OMG 😱

[ComfyUI @ComfyUI]

Seedance 2.0 is on its way to ComfyUI.
Stay tuned!

[Mark Gadala-Maria @markgadala]

The art of ancient Cat Fu.

Coming too a theater near you.

[Mark Gadala-Maria @markgadala]

AI is so much fun.

We need a full Cat Fu movie.

[David Soeiro @David_Soeiro]

@Affinity Thanks

[Google AI Studio @GoogleAIStudio]

⚡️ gemini 3 flash is here

• frontier intelligence built for speed
• pro-grade reasoning at a fraction of the cost
• our most impressive model for agentic workflows

available now as gemini-3-flash-preview in AI Studio and the Gemini API

[Wan @Alibaba_Wan]

Introducing Wan2.6 - A native multimodal model that turns your ideas into breathtaking videos and images!

· Starring: Cast characters from reference videos into new scenes. Support human or human-like figures, enabling complex multi-person and human-object interactions with appearance and voice consistency.

· Intelligent Multi-shot Narrative: Turn simple prompts into auto-storyboarded, multi-shot videos. Maintain visual consistency and upgrade storytelling from single shots to rich narratives.

· Native A/V Sync: Generate multi-speaker dialogue with natural lip-sync and studio-quality audio. It doesn’t just look real - it sounds real.

· Cinematic Quality: 15s 1080p HD generation with comprehensive upgrades to instruction adherence, motion physics, and aesthetic control.

· Advanced Image Synthesis and Editing: Deliver cinematic photorealism with precise control over lens and lighting. Support multi-image referencing for commercial-grade consistency and faithful aesthetic transfer.

· Storytelling with Structure: Generate interleaved texts and images powered by real-world knowledge and reasoning capabilities, enabling hierarchical and structured visual narratives.

[David Soeiro @David_Soeiro]

@GoogleAIStudio I hope this will improve development assistance because I was creating my Python nodes with Gemini, and sometimes it gets stuck on basic problems instead of trying to work around them. That said, it allows you to develop in programming languages without needing to master them 👍

[David Soeiro @David_Soeiro]

@ComfyUI Good job. An option to add nodes thumbnails that don't have them or change the developers thumbnails, would have been useful. Sorting doesn't work for installed nodes. I would also have liked to have a sort by installation date to find last installed nodes
https://t.co/HsP9rClcWk

[David Soeiro @David_Soeiro]

@ComfyUIWiki @c__byrne @ComfyUI Thanks, I'll keep that handy and try to record the bugs I've spotted on video

[David Soeiro @David_Soeiro]

The new "Media Assets" section have missing classes ("comfy-view-side-bar-container" and "comfy-view-side-bar-header"). It's harder to reach every design elements if same elements structure have missing classes. Thanks for your attention 🙏 @ComfyUI @ComfyUIWiki #ComfyUI

[David Soeiro @David_Soeiro]

@c__byrne @ComfyUI @ComfyUIWiki You're welcome, I love ComfyUI. I hope the next update fixes the subgraphs because I use them a lot but I'm encountering quite a few bugs with them. The one that crashes everything when you change the order is very annoying. Do you have a place to report bugs or suggest ideas ?

[David Soeiro @David_Soeiro]

Because of @ComfyUI, I had to buy a 2TB @westerndigital @SanDisk SN8100 NVMe drive. My old SSD @samsung 840 EVO 1TB was too limited in capacity and speed to load very large checkpoints. I'm much more relaxed now, especially since it's joined my two 2TB Samsung 990 Pro drives.

[ComfyUI @ComfyUI]

FLUX.2 is now open-sourced and live in ComfyUI on Day 0！

4MP photorealism, professional lighting/skin/fabric detail, enhanced text rendering, and 10-ref consistency.

Available on Comfy Cloud & local:
- FLUX.2 Dev: BF16 / FP8 partnered with @NVIDIA_AI_PC
- FLUX.2 Pro API: via Partner Node)

Try it in one click: https://t.co/PokNR1BFO8

[David Soeiro @David_Soeiro]

@ComfyUI The very good node "Widget to String" from @Kijaidesign doesn't seem to work with Subgraphs. Does anyone have a solution or an alternative to do the same ? Thanks
https://t.co/xBRBLXSbFI

[David Soeiro @David_Soeiro]

@Affinity Hi, I configured a lot of things on v2. Is there an easy way to migrate all the settings and resources from v2 to v3 ? How can I recover the free police offered to people who had v2 ? I miss the colored icons, it's hard to find what you're looking for with v3 monochrom icons.