rob - comfyui

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 a quick demo to show you how easy it is to go from nodes → app

@ostrisai @ComfyUI Lets gooooooo

HELL YEAH!!! So... this came in the mail. @ComfyUI just changed my world in a big way! This is my dream GPU. I honestly did not think I would ever own one. Thank you so much. You are AMAZING! I am back in business!

Test out the workflow here! comfy.org/workflows/c7c1…

Here's how to get 100% consistent product ads from one seedance 2.0 generation. I did it all in a single chat using the Comfy MCP. The real control here comes from calling my existing workflows (shared below) instead of the agent improvising a pipeline. I directed the agent to call my ComfyUI workflow for cinematic product ads. I specified the close-up shot of the sprite animating, the bezel turn flipping the screen, the display changing to the time 10:04. Now for the consistent variations. The driving video does the heavy lifting but you need to get it right → depthanything v3 pass blended with canny edge lines to show the fine detail... it's why the tiny debossed logo is there → the initial sprite outline lived in those edge lines too, and every gen kept inheriting it. claude suggested a sam3 mask over the screen to hide it (s/o the agent) → with the screen masked, the new star sprite is just prompting: one gpt-image-2 still to generate a reference, one extra line in the seedance 2.0 prompt, and it animates oh and the whole process is a claude skill now.

@mattworkman @Gertywood5 I believe that would be Xindi Zhang blog.comfy.org/p/the-tool-tha…

@Gertywood5 who is this person whom you speak

Amazon AI studio hiring. Too vague to add to WorkmanLabs 😤

@ChetiArt @MedOumoumad Wow🔥 Can’t wait to test it!

I'm working on an LTX 2.3 IC-LoRA that can help you generate a different camera angle view for your videos. I'm planning to share the first PoC version in a week. #cameracontrol #ltx #comfyui

@PurzBeats Claude turn these into native glsl comfy nodes, make no mistakes and also make davinci resolve native in comfy

You can just vibe code davinci resolve plugins. 🤣

@klaywifi The best way to get started these days is with the Desktop App imo (can use local and cloud from one place) comfy.org/download/

@hellorob What a time to be alive. Thx for sharing. I guess this will get me going with comfy finally

Claude Fable running ComfyUI workflows through the Comfy MCP is a cheat code. → Claude pulled the shot from the web, auto-detected the scene cuts + trimmed it → ran my saved depthanything v3 + openpose workflow to build the driving reference video → scrubbed every frame for the sharpest one, then character swapped me in with gpt-image-2 exactly how I directed it: wearing a tuxedo, liminal space environment, no background characters → wrote the seedance 2.0 prompts + ran the gens → stitched together the 3-panel comparison you're watching The preprocessing + prompt writing is usually most of the work on a clip like this. With the MCP I didn't touch any of it. Didn't need to look at a single node lol.

@SamJWasserman 👀

@hellorob I built a desktop app to do this and more I’m open sourcing. Will share later once updated in case useful for anyone. Have a setting in there to export it comfy as well.

@Spectromachina If you feed the original video a lot of the content tends to bleed into the generation

@hellorob This thing where its creating depth map and pose is something seedance already does on its own when you feed it video reference

@AgentOrToy One may still need to understand the nodes to direct them with control

@hellorob the 'didnt touch a single node' era is here and im not emotionally ready comfy mcp just made half the tutorials useless lmao 💀

@icengray Here's some more info on the MCP blog.comfy.org/p/comfy-mcp-tu… And check out some workflows at comfy.org/workflows/

@hellorob Where can I learn to set this up?

@PurzBeats It’s starting to make sense why your last name is Beats

Yeah I dunno have fun with your friends and shit

A whole new way of staying Comfy without the nodes! Will be sharing some tests and advice on using the MCP soon

@SamJWasserman @Blender @dreamina_ai Thanks for sharing!

Finally got this @Blender → Seedance workflow working for not just camera blocking, but character blocking simultaneously. Camera orbit, lens choice, gunfire + cover positions, pop-outs. All directed from pre-vis prior to video generation. Prompt below. Made using @dreamina_ai

@ComfyUI Comfy more comfy? 🫪

We just launched Comfy MCP in public beta, the first MCP built for production pipelines. Connect Claude, Codex, Cursor, or Hermes to the entire ComfyUI ecosystem. → Run any workflow in natural language → Search models, nodes, and templates → Share a workflow URL - your agent picks it up → Re-run saved workflows on new inputs without touching a single node → Hundreds of pre-built workflows. Always auto-updated 20 product-placement images for your brand ads. Character design for your game art. Script-to-shot ideation at scale and so on! Your agent is now a creative technologist.

@jojodecayz 🔥🔥🔥

I recorded this walkthrough of connecting Claude Desktop with Comfy MCP and 3 use cases in Claude! - Batch brand ad variations - Character design & multi poses - Batch 3D generation & connect ComfyUI with Blender Try Comfy MCP: blog.comfy.org/p/comfy-mcp-tu…

@valentynshum Repo is in reply

@hellorob Do you ever share repo?

Krea 2 trained a style I couldn't get into any other model. Midjourney included. It's about time an open source model got there. I've been sitting on this dataset forever. It's of full-page plates from an early-1900s book of watercolor illustrations (via Public Domain Review). The texture and faded tonal gradients with soft bleeding edges tripped up every model I tried... none could get the aesthetic right with decent prompt adherence. Krea 2 nailed it.

@NEXUS_TO_NOVA Thank you 🙌🙌🙌

@hellorob They are magnificent