rob - comfyui (@hellorob) / X

rob - comfyui

872 posts

rob - comfyui

@hellorob

ComfyUI node explorer • Sharing AI workflows • Diffusing pixels and conditioning latent space 🫡

San Francisco, CA

Joined February 2023

Pinned
rob - comfyui
@hellorob
Mar 10
Nodes have always been a huge hurdle for two groups: non-technical creatives wanting to try ComfyUI, and builders with complex workflows they can't easily hand off. App Mode fixes both. Now you get the full power of node-based workflows without looking at a single node. Here's
00:00
00:24
ComfyUI
@ComfyUI
Mar 10
Two massive updates for the ComfyUI ecosystem today: 1️⃣ App Mode: The power of the node graph, now behind an easy-to-use interface. Turn complex workflows into custom apps. 2️⃣ ComfyHub: A brand new home to discover, run, and share community workflows and apps instantly via URL.
36K
rob - comfyui
@hellorob
Oct 5, 2025
Sora 2 blocks input images of real people, making character consistency impossible. I built a workaround so you can have consistent AI UGC actors across videos. Product photo + Prompt → Sora 2 vid → Watermark removal → Character + Wan Animate Step by step guide below ⬇️
00:00
180K
rob - comfyui
@hellorob
Sep 10, 2025
Seedream-4 just unlocked a new paradigm for AI image generation with the ability to generate at 4K resolution… 1 prompt = 4 high resolution variations of your reference image Prompt + FREE one click workflow to crop the images and outpaint to your desired aspect ratio ⬇️
103K
rob - comfyui
@hellorob
Nov 6, 2025
Another win for open-source AI models. This new Qwen Multiple Angles LoRA perfects scene and subject consistency. Look at her ring, the records, album covers and turntable buttons. Even the headphone wire and text. Insane. Test it for yourself - FREE workflow ⬇️
210K
rob - comfyui
@hellorob
Nov 16, 2025
→ Generate base image using Qwen in Comfy → Create variations of scene with Multi Angle Lora → First and Last frame video gen with Veo → Editing tool to cut extra frames (Veo adds frames at the end) → Suno v5 for music All in a couple hours work.
00:00
rob - comfyui
@hellorob
Nov 6, 2025
Another win for open-source AI models. This new Qwen Multiple Angles LoRA perfects scene and subject consistency. Look at her ring, the records, album covers and turntable buttons. Even the headphone wire and text. Insane. Test it for yourself - FREE workflow ⬇️
72K
rob - comfyui
@hellorob
Sep 9, 2025
Fixing plastic AI generated skin is a $100k/month problem. Apps like Enhancor AI use open-source models and ComfyUI workflows as a backend. How do I know this? I built a workflow that clones their core feature and I'm dropping it below for FREE. Same results, no subscriptions.
00:00
75K
rob - comfyui
@hellorob
Sep 15, 2025
Tencent Labs dropped a NEW flux model 'SRPO' and claims it improves realism by 3x over the base model! Sounds too good to be true... I tested it against Flux KREA to see which one delivers more realistic skin texture in portraits See comparisons + my learnings from testing ⬇️
66K
rob - comfyui
@hellorob
Oct 23, 2025
Turns out you can also go from extremely jacked --> skinny
00:00
00:12
A.I.Warper
@AIWarper
Oct 21, 2025
👴For those asking - yes you can also go in the other direction (Old -> Young) 🧒 This was 364 frames @ 1920 x 1072 resolution. Note: As we know what the younger version of the actor should look like this task becomes more difficult to 100% nail the likeness with zero shot
232K
rob - comfyui
@hellorob
Aug 30, 2025
This AI application wasn't possible just 1 week ago. Behold the power of Nano Banana and ComfyUI to Virtually Try On outfits from a flat lay image input + a consistent model. Check below for the final result, FREE workflow, step-by-step guide on how I did this and before/after
00:00
53K
rob - comfyui
@hellorob
Oct 24, 2025
So much potential with this simple workflow: Download viral clip → screenshot first frame → image-edit to swap outfit → WanAnimate
00:00
20K
rob - comfyui
@hellorob
Oct 28, 2025
A Chinese developer with 97 followers just outperformed a SOTA model. He trained an opensource Qwen edit LoRA model for product relighting and it beats Nano Banana across the board. Sounds crazy? Check for yourself. FREE workflow and more comparisons below 👇
25K
rob - comfyui
@hellorob
Aug 14, 2025
The line between what's AI and what's real just got even more blurry... One shot image editing for realistic facial expressions is solved, thanks to the unreleased model in LMArena "nano banana" A comparison of the previous best image editing model (Kontext) vs this new SOTA
48K
rob - comfyui
@hellorob
Nov 4, 2025
Your AI product photos look great until you zoom in on the text... The example below uses the same input image, model and LoRA… the only difference? The workflow. Upscale input → Crop and diffuse ONLY the product → Paste it back FREE workflow and tips below ⬇️
00:00
13K
rob - comfyui
@hellorob
Sep 4, 2025
Get ready for a wave of realistic AI slop to hit your timelines in the next few months... A new Qwen Image LoRA "Boring Reality" was just released on Huggingface by author kudzueye More examples (prompts in alt) ⬇️
15K