@SyntaxDiffusion

-Generative AI solutions & Development- specializing in integrations of Open Source code || I like to make cool stuff

 Philadelphia
instagram.com/SyntaxDiffusion
Joined January 2014
  • Tweets1.8K
  • Following508
  • Followers1.8K
690Media
It’s fall y’all
1
5
267
Syntax Diffusion retweeted
ComfyUI
@ComfyUIOct 19
MOSS-Image is now supported in ComfyUI @OpenMOSS dropped an open-weight image model that has blown up across the community. It’s a 5B model that renders legible text, accepts structure layout prompts and has a high bar for aesthetics. The community has already been cooking up finetunes and LoRAs while the Comfy team has been working to support the model to run seamlessly on any consumer hardware. This model is a must try - check it out.
23
54
14
461
21,773
Exploring Flux 3 Klein from @bfl_ai inside of @ComfyUI 👻🎃
12
463
Syntax Diffusion retweeted
Black Forest Labs
@bfl_aiOct 17
Hey everyone, We've updated our FLUX 3 Image Klein workflows to fix some issues and help you get the best results from the model. • Update to @ComfyUI v0.41.3 and use our updated workflow, link in thread. • We've updated the @huggingface Space as well. To get the best results, the model should be used with our prompt upsampling and 2K resolutions. If you can’t use our prompt upsampling, we’ve also made the recommended system prompt available in our repo to use in your workflows. Thank you for the feedback everyone!
59
49
15
630
47,309
The prizes? ✅ the glory? ✅ #opensourcehiggsfield
ComfyUI
@ComfyUIOct 17
OMW to open source Higgsfield!
1
7
1,873
lets go! Workflows in the link!
ComfyUI
@ComfyUIOct 13
.@NVIDIARTXSpark VFX nodes are now in ComfyUI, with first class support for EXR files format. → RTX Video Super Resolution: upscale, denoise, deblur → RTX Video Frame Generation: new in-between frames → RTX Video HDR: SDR → HDR Runs locally on your RTX GPU. Chain all three to finish footage before it goes back into your VFX pipeline. Click the link below to run the workflows and learn more with our blog ⬇️
1
2
15
2,334
So sick! - seriously in love with this concept
Purz.ai
@PurzBeatsOct 13
Very cool, stumbled on a few of the lines but ff-tracking is really good for kinetic typography lyric videos! Thanks for the idea @SyntaxDiffusion
8
421
Syntax Diffusion retweeted
Purz.ai
@PurzBeatsOct 12
2
4
32
1,151
3
1
9
415
Syntax Diffusion retweeted
Machine Delusions
@MachinedelusionOct 10
Oh yes. Meshes are useless when i can render the entire metropolis of tokyo in a shader compiled into a single HTML file
Keenan Crane
@keenanisaliveOct 9
With everyone busily using LLMs + Blender/Three.js to make 3D models, I thought I'd try a different geometric representation. This dragon isn't a mesh, NeRF, 3DGS, or video model: it's 27kb of GLSL code (generated via LLM), defining a closed-form implicit surface. 🧵 [1/n]
94
248
44
3,614
179,703
Dwight never lies. Made with H3 in ComfyUI!
1
4
498
Chopin's Revolutionary Étude- in Python reads a public domain encoding with mido, snaps it to a 1/24-beat Fraction grid, splits each hand into voices, writes an 808 that follows the left-hand bass into the same score, and synthesizes it all in numpy (Salamander piano, VSCO strings, a sine 808, an FDN hall). The score is then baked into PNG textures and three HLSL compute shaders draw the engraving, the kern terminal and the gold ball live. A checker verifies every note and every ball landing against the audio before each render.
2
8
497
Human movement is fascinating to watch
6
4
1
43
1,827
made in @ood_labs btw
1
98
Syntax Diffusion retweeted
Machine Delusions
@MachinedelusionOct 1
Open 5.5 building a mechanical scorpion walking through a forest. What blows my mind here is there's no models. Its all Shaders, WGLS. Its interactive, you can click around to make the scorpion move and change the entire environment with the parameters on the procedural graph. Even blender is obsolete. Insane.
8
5
83
3,963
Congrats to the BFL team on another banger!
Black Forest Labs
@bfl_aiOct 1
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.
1
10
608
I had a first hand look at how powerful this is, this is a game changer for working live in comfy. Something breaks? It’s got you. Want to wire something up and cannot remember how? It’s got you. Your Comfy personal assistant 🙌
ComfyUI
@ComfyUIOct 1
Comfy Agent is now available to everyone in Comfy Cloud. It plans, builds, and fixes ComfyUI workflows right on your canvas. We strongly believe creators shouldn’t choose between ambition and complexity. Comfy Agent is our answer. While it handles the technical part of Comfy, you can finally focus on visual craft! - It builds while you edit. It sees the assets you see. - Ask anything. Reference anything. - Create your own skills, or use the public ones. Agent in Comfy Desktop is coming soon in a few weeks. Click the link below to try Comfy Agent today ⬇️
6
409
I’ve already started wiring up some workflows- super exciting!
ComfyUI
@ComfyUISep 30
Comfy API is live Point it at a workflow JSON and it handles the rest: → Resolves your custom nodes, models, LoRAs, and Python deps → Pins it all, ComfyUI version included, into a versioned Build → Cuts an immutable release, so what you test is what ships → Deploys as an autoscaling endpoint on RTX PRO 6000, H100, H200, or B200 Click the link below to deploy your first workflow and learn more with our blog ⬇️
1
7
1,122
Maybe 16:9 does the animatronic bots more justice. Opus 5.5 absolutely crushed this. It had access to Comfy Router. It used nano banana, Tripo It modeled in blender It sliced, rigged and modified the geometry It mapped to hlsl in sentinel It created a puppeteer graph It did all of this, because I gave it tools to build.
1
2
1
20
724
Load more