<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/KJNksY9Ur3w" start="0"></iframe></div>☕ One coffee = one happy creator: <a target="_blank" rel="ugc" href="https://buymeacoffee.com/the_frizzy1">https://buymeacoffee.com/the_frizzy1</a><hr />Eight of the nine local MiniMax H3 modes in one workflow, picked from one dropdown. Text to video, image to video, last frame, first+last, references, multiframe, ControlNet pose and Extend a clip. Every mode comes out with sound.<h2 id="what-you-need">What you need</h2>✔ Custom nodes — None. Core ComfyUI only. ✔ ComfyUI version — 0.39.2 for v2.3.0 (native MiniMax H3, SDPose, Switch / Custom Combo / Math Expression, Trim Audio Duration). The benchmark table below was run on 0.37.4. ✔ VRAM — 12 GB — tested, not estimated. Peak 11.3–11.6 GB ✔ System RAM — 32 GB. It peaks at 17–22 GB, so close your other big apps ✔ Tested on — RTX 3060 12 GB · 32 GB DDR4 · ComfyUI 0.37.4 (Sage attention); v2.3.0 on ComfyUI 0.39.2 ✔ Licence — Workflow MIT · MiniMax H3: MiniMax H3 Community License<h2 id="models-to-download">Models to download</h2>Click a file name to download it. Put it in the folder shown, inside <code>ComfyUI/models/</code>. Every file name was read from the workflow <code>.json</code>.Required — all 10 files, about 69 GB. Text and image to video only (including last frame, first + last and extend) needs 5 of them, about 42 GB: the FL2VA model, the FL2V turbo LoRA, the text encoder and both VAEs.<a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3">Comfy-Org/MiniMax-H3</a><h3 id="diffusion_models">diffusion_models/</h3>File: minimax_h3_fl2va_pruned_int8_convrot.safetensors — 21.0 GB (12 GB (tested)) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_fl2va_pruned_int8_convrot.safetensors">https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_fl2va_pruned_int8_convrot.safetensors</a>Put it here: ComfyUI/models/diffusion_models/File: minimax_h3_ref2va_pruned_int8_convrot.safetensors — 21.0 GB (12 GB (tested)) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_ref2va_pruned_int8_convrot.safetensors">https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_ref2va_pruned_int8_convrot.safetensors</a>Put it here: ComfyUI/models/diffusion_models/<h3 id="loras">loras/</h3>File: minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors — 2.0 GB Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/loras/minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors">https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/loras/minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors</a>Put it here: ComfyUI/models/loras/File: minimax_h3_ref2v_turbo_4step_v0.1_comfyui_bf16.safetensors — 2.0 GB Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/loras/minimax_h3_ref2v_turbo_4step_v0.1_comfyui_bf16.safetensors">https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/loras/minimax_h3_ref2v_turbo_4step_v0.1_comfyui_bf16.safetensors</a>Put it here: ComfyUI/models/loras/<h3 id="text_encoders">text_encoders/</h3>File: qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors — 15.7 GB Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors">https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors</a>Put it here: ComfyUI/models/text_encoders/<h3 id="vae">vae/</h3>File: minimax_h3_video_vae_int8_convrot.safetensors — 2.8 GB Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_video_vae_int8_convrot.safetensors">https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_video_vae_int8_convrot.safetensors</a>Put it here: ComfyUI/models/vae/File: minimax_h3_audio_vae_fp32.safetensors — 0.6 GB Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_audio_vae_fp32.safetensors">https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_audio_vae_fp32.safetensors</a>Put it here: ComfyUI/models/vae/<h3 id="model_patches">model_patches/</h3>File: minimax_h3_fun_controlnet_union_pruned_int8_convrot.safetensors — 2.3 GB (ControlNet mode) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/model_patches/minimax_h3_fun_controlnet_union_pruned_int8_convrot.safetensors">https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/model_patches/minimax_h3_fun_controlnet_union_pruned_int8_convrot.safetensors</a>Put it here: ComfyUI/models/model_patches/<a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/SDPose">Comfy-Org/SDPose</a> — the ControlNet mode's pose models.<h3 id="checkpoints">checkpoints/</h3>File: sdpose_wholebody_fp16.safetensors — 1.9 GB (ControlNet mode) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/SDPose/resolve/main/checkpoints/sdpose_wholebody_fp16.safetensors">https://huggingface.co/Comfy-Org/SDPose/resolve/main/checkpoints/sdpose_wholebody_fp16.safetensors</a>Put it here: ComfyUI/models/checkpoints/<h3 id="diffusion_models">diffusion_models/</h3>File: rt_detr_v4-x-hgnet_fp16.safetensors — 0.1 GB (ControlNet mode) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/SDPose/resolve/main/diffusion_models/rt_detr_v4-x-hgnet_fp16.safetensors">https://huggingface.co/Comfy-Org/SDPose/resolve/main/diffusion_models/rt_detr_v4-x-hgnet_fp16.safetensors</a>Put it here: ComfyUI/models/diffusion_models/<h2 id="modes">Modes</h2>One Mode dropdown on the node: T2V (prompt) · I2V (First frame) · Last frame · First + last frame · R2V (Reference 1 + 2, write <code>&lt;Picture 1&gt;</code>, <code>&lt;Picture 2&gt;</code> in the prompt) · Multiframe (references + 3 guide frames at the times you set) · ControlNet pose (Reference 1 + video, the pose is read from it) · Extend a clip.The inputs start bypassed. Un-bypass only the ones your mode uses (select + Ctrl+B) and keep the rest bypassed. Length in seconds is turned into a valid H3 frame count for you: 5 s = 124 frames. Turbo LoRAs are on by default, 8 steps FL2VA and 4 steps Ref2VA, 20 steps with turbo off. Two LoRA slots sit on the node: strength 0 means the file is never even opened.Extend with the clip's sound, new in v2.3.0. The clip's last 0.9 s of sound go in with its last 22 frames. In my test the first 0.9 s of the new clip followed the music's loudness almost exactly with the switch on, envelope match 0.961, and not at all with it off, -0.016. After the join H3 makes new sound for your prompt either way: it did not keep the song going. The result begins with those 22 carried-over frames, so trim about 0.9 s when you join clips.<h2 id="speed-on-my-rtx-3060">Speed on my RTX 3060</h2>Each mode run once, 5 s clips, turbo on. Wall is queue to finished including model loading, sampling is time in the sampler nodes.<ul><li>T2V — 0.4 MP, 3 min 02 s wall, 2 min 28 s sampling, 11.3 GB peak vram, 16.9 GB peak ram</li><li>I2V (first frame) — 0.4 MP, 3 min 20 s wall, 2 min 46 s sampling, 11.3 GB peak vram, 17.1 GB peak ram</li><li>Last frame — 0.4 MP, 3 min 19 s wall, 2 min 46 s sampling, 11.4 GB peak vram, 17.1 GB peak ram</li><li>First + last frame — 0.4 MP, 3 min 29 s wall, 2 min 54 s sampling, 11.3 GB peak vram, 16.9 GB peak ram</li><li>R2V (references) — 0.4 MP, 2 min 10 s wall, 1 min 33 s sampling, 11.4 GB peak vram, 16.9 GB peak ram</li><li>Multiframe — 0.4 MP, 2 min 18 s wall, 1 min 42 s sampling, 11.3 GB peak vram, 16.9 GB peak ram</li><li>ControlNet (pose) — 0.4 MP, 4 min 59 s wall, 2 min 43 s sampling, 11.3 GB peak vram, 20.1 GB peak ram</li><li>Extend, with the clip's sound — 0.4 MP, 3 min 51 s – 3 min 53 s wall, — sampling, 11.4 GB peak vram, 19.1 GB peak ram</li><li>Extend, silent — 0.4 MP, 3 min 31 s – 3 min 33 s wall, — sampling, 11.4 GB peak vram, 19.1 GB peak ram</li></ul>At 0.9 MP (1280x736) every mode also ran: 6 min 31 s for Multiframe up to 13 min 07 s for ControlNet, peak VRAM 11.6 GB, peak RAM 18.5–21.8 GB. Keep Megapixels at 0.4 or 0.9 on 12 GB. 1.5 MP spills out of VRAM: T2V timed out after 32 min, so stay at 0.9 or below.<h2 id="what-did-not-work">What did not work</h2><ul><li>An input you are not using, left un-bypassed, gives you "Invalid image file" before the run even starts. ComfyUI checks the file of every active loader, also in modes that never read it.</li><li>If the mode needs an input and it is still bypassed, the run stops at a "Needs ..." node instead of quietly making a T2V.</li><li>Downloaded only the 42 GB set? The Ref2VA, Ref2V LoRA, ControlNet, SDPose and RT-DETR loaders go red. Click them and pick any file you have in that folder, they are never loaded in the FL2VA modes.</li><li>Loaders red although you downloaded everything: your models sit in a sub-folder like <code>diffusion_models/MiniMax-H3/</code>. Re-pick each red loader once.</li><li>There is no loop node in core ComfyUI yet, so a long video here means running Extend again and again, one clip after another.</li><li>The ninth H3 mode, a full character swap, is not in here. It runs on Viggle's H3 finetune and needs a custom node pack, so it stayed its own workflow.</li></ul><h2 id="get-the-workflow">Get the workflow</h2><ul><li>GitHub: <a target="_blank" rel="ugc" href="https://github.com/Thefrizzy1/The_frizzy1-Workflows/tree/main/workflows/minimax/h3-ultimate-12gb">https://github.com/Thefrizzy1/The_frizzy1-Workflows/tree/main/workflows/minimax/h3-ultimate-12gb</a></li><li>Hugging Face mirror: <a target="_blank" rel="ugc" href="https://huggingface.co/The-frizzy1/The_frizzy1-Workflows/tree/main/workflows/minimax/h3-ultimate-12gb">https://huggingface.co/The-frizzy1/The_frizzy1-Workflows/tree/main/workflows/minimax/h3-ultimate-12gb</a></li></ul>More videos on this stuff: <a target="_blank" rel="ugc" href="https://www.youtube.com/playlist?list=PLMztlpsP7Bgg">https://www.youtube.com/playlist?list=PLMztlpsP7Bgg</a>

MiniMax H3 Ultimate 12GB — T2V/I2V/FFLF/R2V/Multiframe/ControlNet/Extend, one dropdown, with audio

v2.3.0 adds "Extend: keep the clip's sound", so the last 0.9 s of the clip's audio goes in with its last 22 frames and the join does not jump. Tested on ComfyUI 0.39.2.

Files with SHA256: a232483137de21acc5593c1cc72a193523b921e1b468d5994a516f768814b5d0