MiniMax H3 Veda Acceleration | 3x Fast Ref-to-Video
Minimax H3 Latent Upscaler (3D)
Already loads minimax_h3_latent_upscaler_3d_fp16.safetensors
ComfyUI model file · Latent upscale model
Minimax H3 Latent Upscaler 3D (fp16) · Latent-space upscaler for MiniMax H3 video
This is LBH-123-AI’s 3D latent upscaler for MiniMax H3 in fp16. It enlarges H3 video latents directly, so you can generate at low resolution and refine at high resolution without decoding through the VAE. Put it in ComfyUI/models/latent_upscale_models.
The author later renamed this file minimax_h3_latent_upscaler_3d_conv_v1_fp16.safetensors. Both names have the same SHA256.
minimax_h3_latent_upscaler_3d_fp16.safetensors
The short version
MiniMax H3’s video VAE is about 5 billion parameters, so decoding to pixels, upscaling and encoding again is slow. This model upscales the 24-channel H3 latent itself, keeping the time axis, and avoids the ghosting that plain bilinear latent resizing causes.
It was first published as minimax_h3_latent_upscaler_3d_fp16.safetensors, and many workflows still use that name. The author has since moved it to minimax_h3_latent_upscaler_3d_conv_v1_fp16.safetensors; the SHA256 043e5a48…84812eb55c2 is the same, so either name works. The author also released a lighter 2D model in November 2026.
Install
Author’s repo, current filename. Rename it if your workflow asks for the old one.
saves as minimax_h3_latent_upscaler_3d_conv_v1_fp16.safetensors
Same SHA256 under the original filename.
saves as minimax_h3_latent_upscaler_3d_fp16.safetensors
ComfyUI/ └─ models/ ├─ … └─ latent_upscale_models/ └─ minimax_h3_latent_upscaler_3d_fp16.safetensors
$ cd ComfyUI/models/latent_upscale_models$ wget -O minimax_h3_latent_upscaler_3d_fp16.safetensors \$ https://huggingface.co/LBH-123-AI/Minimax_h3_latent_Upscaler/resolve/main/minimax_h3_latent_upscaler_3d_conv_v1/minimax_h3_latent_upscaler_3d_conv_v1_fp16.safetensors$ sha256sum minimax_h3_latent_upscaler_3d_fp16.safetensors# 043e5a48e161610ef6c3ea974645220354d06fa618abca15f76d084812eb55c2
Safetensors files hold tensors only and cannot run code. Still compare the SHA256: a failed download often leaves an HTML error page saved under the model’s filename.
Use
The upscaler works on latents, between a low-resolution H3 pass and a refining pass at the target size. The Minimax H3 Latent Upscaler (3D) node loads the file and upscales in one step.
Minimax H3 Latent Upscaler (3D) comes from the Comfyui_Minimax_h3_latent_Upscaler custom node pack. Install it with ComfyUI Manager first.
LATENT
model_nameminimax_h3_latent_upscaler_3d_fp16.safetensors
scale1.5–2.0
precisionfp16
MinimaxH3LatentUpscaler3D
denoise0.3–0.5
Why latent upscaling
It skips the decode → pixel upscale → encode round trip through H3’s large video VAE.
Scales
The 3D model was trained at 2×, 2.25×, 2.5× and 4×; its author reports weaker results below 1.5×.
Works with
minimax_h3_latent_upscaler_3d_fp16.safetensors is one part of the stack. A workflow that reports a missing model usually needs these too. Use the Ref2VA diffusion model instead of FL2VA for reference-to-video workflows.
| File | Role | Folder | Size | Download |
|---|---|---|---|---|
| minimax_h3_fl2va_pruned_int8_convrot.safetensors | Diffusion model (FL2VA) | models/diffusion_models/ | 20.97 GB | Get |
| qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors | Text encoder (Qwen3-VL 32B) | models/text_encoders/ | 15.69 GB | Get |
| minimax_h3_video_vae_fp16.safetensors | Video VAE | models/vae/ | 5.21 GB | Get |
| minimax_h3_audio_vae_fp32.safetensors | Audio VAE | models/vae/ | 605 MB | Get |
| minimax_h3_fl2v_turbo_4step_v1.0_768p_comfyui_bf16.safetensors | Turbo LoRA, 4 steps(optional) | models/loras/ | 1.96 GB | Get |
Run it
We match workflows by the model files they load: this exact file first, then other versions of it, then workflows built for the same use, then other models from the same family.
5 workflows
These workflows already load minimax_h3_latent_upscaler_3d_fp16.safetensors. Open one and run it as is.
Minimax H3 Latent Upscaler (3D)
Already loads minimax_h3_latent_upscaler_3d_fp16.safetensors
Minimax H3 Latent Upscaler (3D)
Already loads minimax_h3_latent_upscaler_3d_fp16.safetensors
Minimax H3 Latent Upscaler (3D)
Already loads minimax_h3_latent_upscaler_3d_fp16.safetensors
Minimax H3 Latent Upscaler (3D)
Already loads minimax_h3_latent_upscaler_3d_fp16.safetensors
Minimax H3 Latent Upscaler (3D)
Already loads minimax_h3_latent_upscaler_3d_fp16.safetensors
1 workflow
These workflows load another MiniMax H3 model. Select minimax_h3_latent_upscaler_3d_fp16.safetensors in their Minimax H3 Latent Upscaler (3D) node to use it instead.
Minimax H3 Latent Upscaler (3D)
h3_upscaler_lms_v0.1_fp32.safetensors
Replace with minimax_h3_latent_upscaler_3d_fp16.safetensors
Compare
| File | Relation | Size | Best for |
|---|---|---|---|
| minimax_h3_latent_upscaler_3d_fp16.safetensors | This page · original filename | 691 MB | Workflows that use the old name |
| minimax_h3_latent_upscaler_3d_conv_v1_fp16.safetensors | Identical bytes · current filename | 691 MB | Same file |
| minimax_h3_latent_upscaler_3d_conv_v1_bf16.safetensors | Same model · bf16 | 691 MB | GPUs that prefer bf16 |
| minimax_h3_latent_upscaler_2d_conv_v1_fp16.safetensors | Newer 2D model | 364 MB | Half the size, adjustable sharpness; needs the 2D node |
| h3_upscaler_lms_v0.1.safetensors | Fine-tune of this model | 691 MB | Extra perceived sharpness |
Troubleshoot
Why: The workflow asks for this exact filename, but ComfyUI cannot find it in models/latent_upscale_models. Usually the file is missing, sits in a different folder, or was saved under another name such as minimax_h3_latent_upscaler_3d_conv_v1_fp16.safetensors.
Fix: Move the file into ComfyUI/models/latent_upscale_models/, rename it to match the workflow (or pick it again in the dropdown), then refresh the node list or restart ComfyUI.
Why: Minimax H3 Latent Upscaler (3D) is not built into ComfyUI. It comes from the Comfyui_Minimax_h3_latent_Upscaler custom node pack.
Fix: Install Comfyui_Minimax_h3_latent_Upscaler with ComfyUI Manager (or git clone it into ComfyUI/custom_nodes), then restart ComfyUI.
Why: The download is incomplete, or the browser saved an HTML sign-in or error page under the model’s filename.
Fix: Check that the file is exactly 690,592,672 bytes and that its SHA256 matches the value above. Download it again from Hugging Face · LBH-123-AI/Minimax_h3_latent_Upscaler if not.
Rather skip the setup?
Run MiniMax H3 Veda Acceleration in your browser on a cloud GPU. Nothing to download.
FAQ
043e5a48e161610ef6c3ea974645220354d06fa618abca15f76d084812eb55c2 and are 690,592,672 bytes. The author renamed it when the 2D model came out.ComfyUI/models/latent_upscale_models/. Then refresh the node list or restart ComfyUI so Minimax H3 Latent Upscaler (3D) lists the file.Sources: LBH-123-AI/Minimax_h3_latent_Upscaler · ComfyUI node on GitHub
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.