ComfyUI node explorer • Sharing AI workflows • Diffusing pixels and conditioning latent space 🫡
San Francisco, CA
Joined February 2023
- Tweets1K
- Following554
- Followers6.4K
- Likes5.2K
rob - comfyui retweeted
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 ⬇️
rob - comfyui retweeted
The open source community has been delivering on LTX 2.3 LoRAs.
Fine tuning LTX 2.3 unlocks control that you can't get from closed models.
Here are 7 LoRAs that can save your footage.
There are too many incredible LoRAs to cover, so comment below your favorite that needs a showcase!
Links to all the workflows below 👇
rob - comfyui retweeted
LTX-2.3 is now supported in ComfyUI
Major quality improvements from @Lightricks:
- Finer visual details
- Better 9:16 portrait videos
- Cleaner audio
- More stable image-to-video motion
- Smarter prompt understanding
- Clearer text rendering
Examples 🧵👇
rob - comfyui retweeted
Hunyuan 3D 3.0 is now available in ComfyUI via Partner Nodes!
We are bringing more models & tools into ComfyUI, starting with state-of-the-art asset generation from text, images, or sketches.
Coming soon in ComfyUI:
- texture editing
- semantic UV unwrapping
- intelligent 3D part decomposition
The goal isn’t to replace 3D artists.
It’s to remove the non-creative friction so real creative moments can happen faster.
rob - comfyui retweeted
LTX-2 is natively supported in ComfyUI on Day 0 🎬🔊
The next chapter in controllability for open-source video generation.
- Open-source audio-video foundation model
- Generates motion, dialogue, SFX, and music together
- Canny, Depth & Pose video-to-video control
- Keyframe-driven generation
- Native upscaling and prompt enhancement
Everything in a single pass.
rob - comfyui retweeted
Okay so hear me out-
Running models locally is cool, and I understand why it's important, but I have never felt more free to build and test things than using an API with a good set of features.
Like it's not even close. I can iterate on ideas in less than 1/10th the time.
rob - comfyui retweeted
it takes 3 days to learn diffusion models top down, 6 years before you can learn it bottom up (academia)
historically you couldn't start learning about diffusion and then get into the math cause it's an unscalable way to teach students since it's so unstructured. but now you can ask claude recursively to teach you every single detail down to every single math intuition, which very soon will change how we see education
rob - comfyui retweeted
Vae encoder for mochi
Can you say local vid2vid ? 🎯🎯🎯🎯
magnet:?xt=urn:btih:OCTUFNZV2DGSE457NRITOPRPGE7LBMNG&dn=encoder&tr=udp%3A%2F%2Ftracker.opentrackr.org%3A1337%2Fannounce
Mochi 1 Encoder.
Live on HuggingFace and our Github Repo. Happy Halloween!
