<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/2eaY7fs70iA" 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 />An invented character, the same face again in any scene, and video of them, on one 12 GB card. Four workflows in one download: two new ones on MiniMax H3 Image (core ComfyUI nodes only) and the two video workflows I used with them. Every prompt from the video is in the zip.Detailed step-by-step guide on GitHub: <a target="_blank" rel="ugc" href="https://github.com/Thefrizzy1/The_frizzy1-Workflows/tree/main/workflows/minimax/ai-influencer-12gb">https://github.com/Thefrizzy1/The_frizzy1-Workflows/tree/main/workflows/minimax/ai-influencer-12gb</a><h2 id="the-four-workflows">The four workflows</h2><ul><li>1 · AI Influencer 1, create the character: a text prompt gives you the first picture of an invented person.</li><li>2 · AI Influencer 2, same face, new scene: their close-up plus a prompt puts the same person somewhere else. With a second picture it puts them into a frame of your own video (the keyframe for the swap).</li><li>3 · AI Influencer 3, Viggle Remake swap: a clip plus one painted keyframe gives the same clip with your character, the clip's sound kept. The graph I ran, built on Viggle Remake.</li><li>4 · MiniMax H3 Ultimate 12GB: a still to a 10 second clip with sound, and the last frame of a clip as the first frame of the next for longer ones.</li></ul>Workflows 1 and 2 are enough for an account that posts pictures. 3 and 4 are optional, only for video.<h2 id="what-you-need">What you need</h2>✔ Custom nodes: none for workflows 1 and 2 (core ComfyUI only). Workflow 3 needs Viggle's node pack (folder comfyui/ComfyUI-Viggle-Remake in <a target="_blank" rel="ugc" href="https://huggingface.co/Viggle/Viggle-Remake">Viggle/Viggle-Remake</a>).✔ ComfyUI version: 0.45 or newer. Older versions do not have the MiniMax H3 Image node. 0.45.0 tested.✔ VRAM: 12 GB, tested, not estimated. Peak 11.6 GB.✔ System RAM: 16 to 22 GB peak, in a 32 GB machine.✔ Tested on: RTX 3060 12 GB · Ryzen 5 5600X · 32 GB DDR4 · ComfyUI 0.45.0✔ Licence: workflows MIT · MiniMax H3 Image and MiniMax H3: MiniMax community licenses (check them before commercial use).<h2 id="models-to-download">Models to download</h2>Click a link to download the file. Put it in the folder shown, inside ComfyUI/models/.Required for workflows 1 and 2: 3 files, 29.4 GBFile: minimax_h3_image_pruned_w4a8.safetensors (12.5 GB) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3-Image/resolve/main/diffusion_models/minimax_h3_image_pruned_w4a8.safetensors">https://huggingface.co/Comfy-Org/MiniMax-H3-Image/resolve/main/diffusion_models/minimax_h3_image_pruned_w4a8.safetensors</a> Put it here: ComfyUI/models/diffusion_models/File: qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors (15.7 GB, the same file MiniMax H3 video uses) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3-Image/resolve/main/text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors">https://huggingface.co/Comfy-Org/MiniMax-H3-Image/resolve/main/text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors</a> Put it here: ComfyUI/models/text_encoders/File: minimax_h3_image_vae_fp16.safetensors (1.2 GB) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3-Image/resolve/main/vae/minimax_h3_image_vae_fp16.safetensors">https://huggingface.co/Comfy-Org/MiniMax-H3-Image/resolve/main/vae/minimax_h3_image_vae_fp16.safetensors</a> Put it here: ComfyUI/models/vae/Optional, only for video (workflows 3 and 4)File: viggle_remake_swap_pruned_int8_convrot.safetensors (21.0 GB, workflow 3) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Viggle/Viggle-Remake/resolve/main/int8/viggle_remake_swap_pruned_int8_convrot.safetensors">https://huggingface.co/Viggle/Viggle-Remake/resolve/main/int8/viggle_remake_swap_pruned_int8_convrot.safetensors</a> Put it here: ComfyUI/models/diffusion_models/File: minimax_h3_video_vae_fp16.safetensors (5.2 GB, workflow 3) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_video_vae_fp16.safetensors">https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_video_vae_fp16.safetensors</a> Put it here: ComfyUI/models/vae/File: minimax_h3_audio_vae_fp32.safetensors (0.6 GB, workflows 3 and 4) 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/File: minimax_h3_fl2va_pruned_int8_convrot.safetensors (21.0 GB, workflow 4, image to video) 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_video_vae_int8_convrot.safetensors (2.8 GB, workflow 4) 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_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors (2.0 GB, workflow 4) 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/Workflow 4 has more modes than image to video. The files for those are listed in <a target="_blank" rel="ugc" href="http://downloads.md">downloads.md</a> in the zip and on GitHub.<h2 id="step-by-step">Step by step</h2><ol><li>Create the character (workflow 1): describe the person like a photo caption: who, hair, glasses, jewellery, outfit, place, light, lens. Long prompts work best. 3:4 at 7.5 MP is what I used. The same prompt with another seed is another person.</li><li>Make the reference (workflow 1 again): a close-up with both eyes visible. A half-body shot gives the face too few pixels, and every scene made from it looked worse in my tests.</li><li>The same face in a new scene (workflow 2): the close-up as Picture 1, Picture 2 stays bypassed. Start the prompt with "The woman from &lt;Picture 1&gt;, the same person with the same face..." and then describe the new place and outfit.</li><li>A reference sheet (workflow 2): the same, with a prompt that asks for four views on one picture: front, side, behind and a close-up.</li><li>Video from a still (workflow 4, optional): image to video with a scene picture as the first frame. I ran 576x736, 10 seconds, turbo LoRA.</li><li>Swap the character into a clip (workflows 2 and 3, optional): cut the clip to 90 to 345 frames at 24 fps on the grid 17n+5. Take one frame, paint the character into it in workflow 2 (Picture 1 = the frame, Picture 2 = the close-up, Ctrl+B switches Picture 2 on), then run workflow 3 with the clip and that keyframe. The clip's own sound is kept.</li></ol><h2 id="speed-on-the-rtx-3060-12-gb-(cold-start-model-loading-included)">Speed on the RTX 3060 12 GB (cold start, model loading included)</h2>Workflow 1, text to image: 3 MP 0:36 · 7.5 MP 0:51 to 0:54 · 16 MP 1:54Workflow 2, one picture, 7.5 MP: 1:46 to 1:48 · two pictures (keyframe, 2880x1632): 2:13 to 2:22Workflow 3, Viggle Remake swap: 832x480, 124 frames 6:37 · 1056x608, 90 frames 8:34Workflow 4, image to video, 576x736, 10 seconds: 7:55 to 9:05 · three clips in a row (30 seconds): 24:19Render the swap bigger than the 480 benchmark: faces are small at that size, and 608 looked clearly better on the same card. The quality is your call.<h2 id="what-did-not-work">What did not work</h2>At 16 MP something went wrong in the generation on my setup (same prompt and seed as the 7.5 MP picture), so I stayed at 7.5 MP. At 3 MP the face gets soft.A half-body shot as the reference gave worse scenes than a close-up.Small things drift between pictures. In mine: the shape of the sunglasses, and tattoos on the hands in one scene.Over three clips in a row (30 seconds) the face drifted at the end.Out of memory: lower the size, or for video make the clip shorter.<h2 id="where-the-line-is">Where the line is</h2>Good uses: UGC-style content, a product video, an ad for your own things, a character for your channel. Label it as AI when you post it. If you swap a character into somebody else's clip, say so. The character in the samples is invented; no real person's photo was used as a reference.<h2 id="get-the-workflow">Get the workflow</h2>GitHub (guide, prompts, all four files): <a target="_blank" rel="ugc" href="https://github.com/Thefrizzy1/The_frizzy1-Workflows/tree/main/workflows/minimax/ai-influencer-12gb">https://github.com/Thefrizzy1/The_frizzy1-Workflows/tree/main/workflows/minimax/ai-influencer-12gb</a>More videos on this stuff: <a target="_blank" rel="ugc" href="https://www.youtube.com/playlist?list=PLG_da2oqTx7k">https://www.youtube.com/playlist?list=PLG_da2oqTx7k</a>

AI Influencer 12GB — 4 workflows: create a character, same face in new scenes, Viggle Remake swap, MiniMax H3 video

v1.0.0: four workflows in one zip. AI Influencer 1 (create the character) and 2 (same face, new scene) on MiniMax H3 Image, core ComfyUI nodes only. AI Influencer 3 is the Viggle Remake swap graph I ran on an RTX 3060 12 GB. 4 is MiniMax H3 Ultimate 12GB v2.3.0 for image to video. Every prompt from the video is included.

Files with SHA256: d0ddd31b5230de2283f763f5d631249b685c4564ed8724a274291c784ca4e7f7