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.
Perfil de execução
Trecho da fonte
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.
Estimativa de requisito VRAM
Estimativa indisponível
101 GB distribuídos em 7 de 10 arquivos de modelo. Total de arquivos do modelo + 25% de overhead de carregamento + 2 GB de buffer de execução, arredondado para cima.
Requisitos
Requisitos 10Fontes
1 fonteTrechos de fonte
2 trechosSource context: 1082 downloads · Type Workflows · Base model MiniMax H3
gemma_3_12B_it-int8_convrot.safetensors
Não resolvidoText encoder · Unknown
ltx-2-19b-distilled.safetensors
EncontradoVAE · 40.4 GB · Hugging Face · Lightricks/LTX-2
Upscaler · 950 MB · Hugging Face · Lightricks/LTX-2
ltx-2.3_text_projection_bf16.safetensors
Não resolvidoText encoder · Unknown
Checkpoint · 20.0 GB · SAFETENSORS · Hugging Face · kijai/ltx2.3_comfy
LTX23_video_vae_bf16.safetensors
Arquivo não verificadoVAE · Hugging Face · LTX23 Video VAE Bf16.safetensors
minimax_h3_audio_vae_fp32.safetensors
EncontradoVAE · 577 MB · SAFETENSORS · Hugging Face · Comfy-Org/MiniMax-H3
Checkpoint · 19.5 GB · SAFETENSORS · Hugging Face · Comfy-Org/MiniMax-H3
minimax_h3_video_vae_fp16.safetensors
EncontradoVAE · 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