Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
Basically, it generates in low resolution first and then finishes at the high resolution. It uses just the basic latent upscale, so it's a bit unstable—but hey, it's just for my own use anyway.
Runtime profile
Source excerpt
Basically, it generates in low resolution first and then finishes at the high resolution. It uses just the basic latent upscale, so it's a bit unstable—but hey, it's just for my own use anyway.
Estimated VRAM requirement
Estimate unavailable
101 GB across 7 of 10 model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.
Requirements
10 requirementsSources
1 sourceSource excerpts
2 excerptsSource context: 1082 downloads · Type Workflows · Base model MiniMax H3
gemma_3_12B_it-int8_convrot.safetensors
Not resolvedText encoder · Unknown
VAE · 40.4 GB · Hugging Face · Lightricks/LTX-2
Upscaler · 950 MB · Hugging Face · Lightricks/LTX-2
ltx-2.3_text_projection_bf16.safetensors
Not resolvedText encoder · Unknown
Checkpoint · 20.0 GB · SAFETENSORS · Hugging Face · kijai/ltx2.3_comfy
LTX23_video_vae_bf16.safetensors
File unverifiedVAE · Hugging Face · LTX23 Video VAE Bf16.safetensors
VAE · 577 MB · SAFETENSORS · Hugging Face · Comfy-Org/MiniMax-H3
Checkpoint · 19.5 GB · SAFETENSORS · Hugging Face · Comfy-Org/MiniMax-H3
VAE · 4.85 GB · SAFETENSORS · Hugging Face · Comfy-Org/MiniMax-H3
Text encoder · 14.6 GB · SAFETENSORS · Hugging Face · Comfy-Org/MiniMax-H3
Source context: 1077 downloads · Type Workflows · Base model MiniMax H3
