! Image to Video generations should be fixed now !
V7.5 Update
Image to Video generations should be fixed now.
***- PLEASE leave some kind of feedback after trying -
Base Information
Now actually the fastest HQ audio + video generation workflow. See for yourself in the examples. I can currently create these 8s, 1 megapixel videos in 3.5 minutes which is INSANE if you ask me, while keeping good audio!
I'm still experimenting with different scenarios, tweaking for the ultimate best balance of quality vs speed. There might be more updates very soon.
WHY 2 MODELS AND REFINEMENT AT ALL??
Yes, valid question. My answer: creating high resolution videos with the Fast H3 model takes much longer than this workflow, and the quality of the short Taomate turbo workflow is outright bad with low steps. The Solution: We use the power of the audio quality and base movement of the Fast H3 model while then using the ultra-rapid speed of the Taomate 3 step turbo lora to refine and enhance the video to High Quality!
PLEASE let me know how this works for you!
This is my very first attempt at making a FAST workflow that runs on my 16gb + 32gb System RAM Setup and I'm looking forward to see if you guys have the same results like me.
Please try it out and let me know what you think!
INSTRUCTIONS:
Use the green nodes to configure your resolution, aspect ratio & duration
Keep the aspect ratio the same for the first pass and second pass resolution selector
Add your desired LoRAs in the purple node
Enable or Bypass your desired 1st Frame or Last Frame input Image Groups on the left side of the workflow
Adjust to your desired VAE's, text encoders that you might already have (I'm using a new KJ video vae that is smaller)
Don't forget to adjust the filename and path in the Save Video node to your prefered syntax and location (the one in the workflow creates this type of filename syntax with MP, date and time of generation: 1MP_Video_210926-150209_24fps_00001_.mp4)
MODELS
Base FLF2VA / T2V model: https://huggingface.co/Comfy-Org/MiniMax-H3/blob/main/diffusion_models/minimax_h3_fl2va_pruned_int8_convrot.safetensors
Text Encoder: https://huggingface.co/Comfy-Org/MiniMax-H3/blob/main/text_encoders/qwen3vl_32b_minimax_h3_int8_convrot.safetensors
Audio VAE: https://huggingface.co/Comfy-Org/MiniMax-H3/blob/main/vae/minimax_h3_audio_vae_fp32.safetensors
Taomate 3 Step Turbo Lora: https://huggingface.co/drbaph/MiniMax-H3-Turbo-Lora-ComfyUI/blob/main/experimental/minimax_h3_taomate_fl2va_3step_ema_comfyui.safetensors
H3 Latent Upscaler: https://github.com/LBH-123-AI/Comfyui_Minimax_h3_latent_Upscaler
Custom Nodes Links
GENERATION SPEED:
On 5070Ti with 32gb System RAM:
8 seconds - 1 MP resolution: ~3:30 minutes
8 seconds - 0.5 MP resolution: ~1:45 minutes
10 seconds - 1 MP resolution: ~4:30 minutes
10 seconds - 0.7 MP resolution: ~3:10 minutes
Description
I2V generations back on the menu
FAQ
Comments (3)
In the first week of mm H3 being released, with the help of claude and chatgpt, I created a workflow that has no cap on video length, and stays coherent. But that isn't all, it also allows for no cap on references, of course works with first and last and anchor images (between first and last), and references. It allows extending and replacing and editing videos. Allows matching audio to video or matching video to audio. And actually a shit ton more. However, after my first week i continued working on it to extend the shit out of it, and have not stopped since, as of last night with a 5060 ti, i continued extending towards my last goal of making generate video at faster than real time. Generating a 3 minute video in only 160 seconds. Imagine what i am saying is true. Then imagine I didn't scratch the surface, literally of what i have built into the workflow. So if this is true (and it is) why haven't i released it? Well, if i could actually make some money for my non-stop efforts, I would. However it seems to me, it is more valuable to just keep creating not-slop youtube videos, because if i share it, then everyone will be able to have these abilities, and if i make it a paid workflow, it will just get stolen and reposted, so the reason everyone hasn't had this workflow for the last 5 weeks is because it would unlock such capabilities that i would have competition on youtube. However I would post it for 10k dollars and then i wouldn't care about it getting reposted for free. If anyone is rich and wants this, PM me and we can figure out the details.
the "PowerLoraLoaderV2" node doesnt seem to work no matter what i tried installing "comfyui-sa-nodes-qq" it just doesnt work
@JJoker375
Did you try installing it via Git URL and the ComfyUI Manager? Also, did you try the nightly version instead of the "latest" version? I have the link to the nodes in the description.