Activity
Mon
Wed
Fri
Sun
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
What is this?
Less
More

Owned by Andy

Muse Collective

409 members • Free

Cancel your AI subscriptions. Build local instead. Create AI characters & content with free, open-source tools, no monthly fees.

ICEKIUB - AI Tech and ComfyUI

1.4k members • Free

Skoolers

162.6k members • Free

AI Sales Agency Launchpad

15.5k members • Free

AI Automation Society

446.2k members • Free

22 contributions to Muse Collective
What do you want help with most right now?
Building the roadmap around what's actually useful to you. Pick the one you'd get the most value from next, and I'll try to turn it into tutorials/workflows.
Poll
30 members have voted
0 likes • 10d
@Mona Leggett what is the vram on a 5080?
0 likes • 5d
@Michael Cunningham hi Michael, thanks for your feedback and I totally get where you are coming from. There are basically 2 things here that are at play. When I created the community it was aimed at those with absolutely no experience with comfyui and to stop them going down the rabbit hole of subscription sites. So it makes sense to gate the lessons as skipping too far ahead means they will just get stuck and not understand more advanced workflows without the proper grounding. I fully plan on changing the levels but need to make sure there is a community to work with first. We are nearly at 400 members which is great. Once I hit 500 which I think is a decent size community then as stated the model will change to paid entry into the community which just reflects the time and effort in both the workflows and bringing people into the community. Those already in the community will stay free but those that enter after 500 will be subject to the subscription charge. I don't know if you have been a part of one these skool communities before but from what I have seen the leveling up seems to be a part of how the best ones work. It's basically an incentive to interact and share ( which i understand, may not be what you are looking for). Hope that explains a little.
MiniMax H3 Example and Prompt Director V1
Ok so here is an example i just created with the Director node. I only did it at 0.2 so I would have a fast render. Duration 30 seconds, chunk set to 15, so it does 2 runs. Took 382.33 secs on my 5090, so expect longer with lower vram cards. Or if you have quantized models swap them out and use them. Prompt: --- Chunk 1/2 (~15.0s) --- subject_definitions: <Subject 1> is a young woman with bright blue hair and fair skin tone, wearing a black baseball cap, light grey bomber jacket, white ribbed tank top, dark grey cargo pants, and black and white sneakers (from `<Picture 1>`). <Subject 2> is a futuristic corridor, marked by white walls, glowing blue LED strips, and a large screen displaying a vessel schematic. (from `<Picture 2>`). summary: [reference generation] The target video shows <Subject 1> and <Subject 2>. retention_analysis: <Subject 1> (referenced in this shot): fully_preserved - matches `<Picture 1>`. <Subject 2> (referenced in this shot): fully_preserved - matches `<Picture 2>`. detailed_description: Clean, bright sci-fi photography, even white and cool-blue lighting, sharp reflective metal surfaces, smooth steady camera movement, crisp modern digital look. [Shot 1] <Subject 1> (S1) continues: She steps into the corridor through a side door, glancing up at the glowing wall screens as she walks, camera tracking alongside her at a relaxed medium shot. [Shot 2] At 00:07.500, She slows and stops in front of one of the status screens, tilting her head as she reads it, one of the panels flickers briefly. Camera pushes in slightly to a close shot on her curious expression. overall_soundscape: Soft hum of ship systems, a faint air-circulation hiss, quiet footsteps on the metal floor, an occasional low electronic beep from a wall panel. non_diegetic_music: Light, minimal electronic pulse underneath, subtle and unobtrusive, never overpowering the dialogue. --- Chunk 2/2 (~15.0s) --- subject_definitions: <Subject 1> is a young woman with bright blue hair and fair skin tone, wearing a black baseball cap, light grey bomber jacket, white ribbed tank top, dark grey cargo pants, and black and white sneakers (from `<Picture 1>`).
MiniMax H3 Example and Prompt Director V1
Marilynilike
One of my earlier gens for a Muse Collective Ad
Marilynilike
1 like • 11d
@Ted Darling thank you. Models like Seedance are amazing and can do a lot of things that local models just can't, which is usually down to consumer hardware. But.... we are catching up! I'm also using the new minimax H3 model and that is outstanding and some say, it rivals Seedance. Ok... I wouldn't quite go that far but it's bloody good 👍
KREA 2!
I love this new model! Not only is it good at realism. You can get it to spit out multiple styles. This is my new Krea2 Marilyn-inspired LoRA. Same ref image, different styles.
KREA 2!
0 likes • Jul 20
@John Feeley thanks John
0 likes • 15d
@Ted Darling interesting. I used the Qwen model too, I just didn't like the way it output people.
workflow rea 2 Edit in ComfyUI – Face Swap request
Hi team, how to download workflow rea 2 Edit in ComfyUI – Face Swap + Reference Boost Workflow?
0 likes • 19d
Here you go Attila
1-10 of 22
Andy Whittaker
4
69 points to level up
@andy-whittaker-4008
Nerdy Photographer from the UK. Working with AI rather than against it!

Active 7h ago
Joined May 13, 2026