Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More
5 contributions to Muse Collective
Speedup Help Needed
I've run 2 generations, using 3 characters and a location image with an output of 15 seconds. - The first run I used the Muse MiniMax H3 Unified Loader (POC) node and it took 24 minutes - The next run I used the New Subgraph node and it took 36 minutes Any suggestions on how I can speed up the workflow? It would take me a considerable amount of time to create a 90 minute series at this rate. Any suggestions are greatly appreciated! I have an RTX 3090, 24 GB VRAM and 64 GB installed ram, Windows, below is an image of the models used.
Speedup Help Needed
0 likes • Sep 8
Exactly as Andy wrote. First of all, all kinds of Turbo LoRAs lead to a greater or lesser degree of quality degradation. SageAttention or dedicated H3 Sol-Attn for MiniMax work better here. Second, on lower-end hardware, it's worth dropping the resolution first and upscaling later. Third, automated setups—like the example loader that automatically adjusts parameters, or various convenient "Director" nodes—can consume more resources. Fourth, you've only shown the loader and models, but we'd need to inspect the entire workflow. And finally, finding a bottleneck requires live monitoring: are you running out of VRAM? RAM? Is the system aggressively swapping data between them? etc., etc. On top of that, for MiniMax, you have to look for the "sweet spot." The resolution/length combination isn't linear in its case. For example, at a given resolution, the generation time increases steadily up to 7 seconds, but jumps drastically from 8 seconds onward. Conversely, keeping the duration fixed while increasing resolution also has a sweet spot beyond which the time suddenly spikes. You also need to pick the right models; sometimes a smaller model will give you the same quality, and we have plenty of options here—fp8, fp16, pruned, int8, etc. And keep in mind, every additional LoRA adds overhead :>
Optimization
I like the concept of the group. But isn't the Skool format a bit impractical for discussions and detailed feedback? Wouldn't something like a forum or Discord work better, for instance? It's a bit clunky here.
Music Video
I am almost there with the fix on my music video element on my minimax workflow. Perfect lipsync, 60 seconds long but the character degrades. Once that is done the new version will be released!
Music Video
0 likes • Sep 7
@Andy Whittaker 5090 is great. After switching from 5080 to 5090, you can finally mess around stress-free. Sure, a 6000 Pro would come in handy occasionally for heavy animate workflows, but that's only once in a while, so RunPod and others take care of business :>
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
97 members have voted
0 likes • Sep 7
And I don't know what I'm trying to achieve :> I'm playing around with many "environments." ComfyUI and WAN2GP, etc., as well as ready-made solutions like Simp... UltraM... etc. (supposedly, I can't advertise, so I won't mention it). Basically, it's just fun for fun, with no real purpose :P
Welcome to Muse Collective (Start Here ✨)
AI can now do things that used to need a studio, a crew and a big budget. Create photorealistic images. Build characters that look the same every time. Clone a voice and make it speak. Turn a still image into video, lip-sync it, even put it to music. And do it all on your own computer, without a stack of monthly subscriptions. Muse Collective is the place to learn how, whether you've never opened ComfyUI or you're already building advanced video and character systems. Not hype. Not theory. We build here. How it works: 🟢 Free for everyone: the community, the classroom lessons, and a lot of workflows, including free video, lip sync and MiniMax H3 workflows. You can go a long way without paying anything. 🟠 Paid tier: where all my advanced nodes and workflows are kept. Upgrade to get the advanced nodes I've built myself, for video, images and more, plus the ready-to-run workflows that use them. If you're in, you're ready to: ✅ Create a realistic AI twin of yourself or an AI Character ✅ Generate professional AI images and video ✅ Clone your voice and bring your character to life ✅ Make your digital twin/character work for you! ✅ Create Music Videos with perfect Lipsync ✅ Bring a story to life with MiniMax H3 workflows Step 1: Introduce yourself below 👇 (copy and paste this) 👤 Name & where you're from? 🎯 What's your goal from AI in the next six months? 🤖 Which level are you starting at? (Beginner / Intermediate / Advanced) 🔧 What do you need most help with right now? How this community works: 💡 Share wins, workflows, and experiments, even the rough early ones 🤝 Drop a like and comment on others' posts, it costs nothing and means everything 🧠 Ask questions openly, post here for community feedback or DM me for support 📈 Share your AI twin, or video, or images as you build them. Progress posts are celebrated here ❌ Zero self-promotion. Zero. This isn't a platform for self-promotion. You will be removed without warning. Step 2: Head to the Classroom tab. Start with Welcome & Roadmap, then work through the levels in order.
1 like • Sep 7
👤 Name & where you're from? - Wojciech, Poland 🎯 What's your goal from AI by end of 2026? - learning learning learning..... 🤖 Where are you in your journey? (Total beginner / some experience / advanced) - advanced 🔧 What do you need most help with right now? - Nothing :>
1-5 of 5
Wojciech Solarczyk
1
2 points to level up
@wojciech-solarczyk-3553
Nothing

Active 12h ago
Joined Sep 7, 2026