MiniMax H3 Image Morning Briefing 2026-11-15 | Top Pick: AI Influencer 12GB — 4 workflows: create a character, same face in new scenes, Viggle

This issue reviews 4 new versions of H3 Image, with 1 rated A, 2 rated B, and 1 rated C. Top pick: AI Influencer 12GB workflow collection: use H3 Image native nodes on a 12 GB GPU to first create a character, then place the same face into new scenes; the author lists all model files and placement paths. The one-click installer v2.0 with visual prompt expansion only changed LLM instructions and preset styles, with just 1 examples, so it was downgraded to B; the Fyre character LoRA includes complete training configuration, rated B; the introductory workflow with only a one-sentence description is rated C.

Zhenzhen's AI Radar · MiniMax H3 Image · 2026-11-15 Morning Briefing

This issue features 4 new versions: Strongly Recommended 0 · Recommended 1 · Worth Watching 2 · Listed Only 1

Editor's Note This issue reviews 4 new versions of H3 Image, with 1 rated A, 2 rated B, and 1 rated C. Top pick: AI Influencer 12GB workflow collection: use H3 Image native nodes on a 12 GB GPU to first create a character, then place the same face into new scenes; the author lists all model files and placement paths. The one-click installer v2.0 with visual prompt expansion only changed LLM instructions and preset styles, with just 1 examples, so it was downgraded to B; the Fyre character LoRA includes complete training configuration, rated B; the introductory workflow with only a one-sentence description is rated C.

Recommended (1)

[A] AI Influencer 12GB — 4 workflows: create a character, same face in new scenes, Viggle Remake swap, MiniMax H3 video · v1.0.0

Workflow · New Model · Author The_frizzy1 · Published 11-15 03:11 · Downloads 31

A collection of four workflows: use H3 Image text-to-image to create a fictional character, then use close-ups + prompts to place the same face into new scenes; also includes two video workflows for Viggle Remake person swapping and H3 image-to-video.

Images

Example 1600x2140

Reasons for Recommendation

  • Serves "multiple scenes for the same character": Workflows 1 and 2 use only ComfyUI native nodes; accounts that only post images can suffice with these two.
  • The author states it was tested on an RTX 3060 12 GB, with peak VRAM usage of 11.6 GB; ComfyUI requires version 0.45 or newer (older versions lack H3 Image nodes).
  • Easy to follow: The model card lists file names, sizes, download addresses, and placement directories one by one; the archive contains all prompts used in the video, and GitHub has a step-by-step guide.

How to Use

  • Workflows 1 and 2 require 3 files: minimax_h3_image_pruned_w4a8 (diffusion_models), qwen3vl_32b_minimax_h3_nvfp4_awq (text_encoders), and minimax_h3_image_vae_fp16 (vae).
  • When creating a character, write the description like a photo caption, detailing the person, hairstyle, accessories, clothing, location, lighting, and camera; the author states that longer prompts work better.
  • Workflow 3 requires the Viggle node pack; Workflow 4 uses the official minimax_h3_fl2v_turbo_8step acceleration LoRA for image-to-video generation.

Risks and Limitations

  • Only 2 visible examples are shown, while 3 are hidden; the page contains mixed content.
  • The video part models are large (a single diffusion model is approximately 21 GB), with peak system memory usage of 16–22 GB.
  • The workflows are MIT licensed, but H3 / H3 Image weights are under the MiniMax Community License; verify commercial use terms yourself before use.

Worth Watching (2)

[B] H3 Image with uncensored vision (installer + workflow) · v2.0

Workflow · Version Update · Author Torque · Published 11-14 22:16 · Downloads 131

Windows one-click installer + workflow for H3 Image: one workflow handles both text-to-image and multi-reference editing of up to 15 images, with a prompt expansion model that can "see" images.

Images

Example 2281x1687

Reasons for Recommendation

  • Version update: The author only noted "improved LLM instructions, added preset styles".
  • Features: Images on the reference board are automatically labeled as <Picture N>; the expander analyzes the images and expands short prompts into long descriptions; optional official 9B expander or 27B Bonsai LLM.
  • The installer automatically selects GGUF quantization based on VRAM (Q5_K_M for 24 GB and above), uses NVFP4 text encoders for RTX 50 series, and int8 for others.

How to Use

  • After unzipping, run Install_H3Image.bat, read the license, and type YES; after installation, run Start_H3Image.bat and load H3Image_Studio in the workflow browser (W).
  • Leave the reference board empty for text-to-image, or add images for editing; requires approximately 56 GB of free disk space.

Risks and Limitations

  • The author self-describes as "vibe coded"; the installation script downloads and pins a specific ComfyUI v0.45.0 portable version and numerous models (approximately 40 GB, including Bonsai approximately 49 GB).
  • Tested only on RTX 5090 32 GB; only 1 visible examples.
  • "Uncensored vision" in the name refers to the expansion model not applying content filtering; the author did not provide further explanation.

[B] Fyre (fictional character) · h3-image-v01

LoRA · Port · Author jandordoe · Published 11-14 23:49 · Downloads 32

H3 Image character LoKr for Fyre, a fictional red-haired freckled woman, including complete ai-toolkit training configuration; can serve as a reference for training characters with H3 Image.

Images

Example 3552x4736

Reasons for Recommendation

  • Port: The same character already has versions for MOSS, Qwen 2.1, Krea 2, Wan 2.2, etc.; the H3 Image version was trained for 3,000 steps using ai-toolkit + Ostris training adapter.
  • Training parameters are fully documented: lokr factor 4, automagic v3, LR 0.0005, EMA 0.98; the configuration file config-h3-image-v01.yml is included.
  • The author states that good similarity was achieved at 2,000 steps, with slight improvement at 3,000 steps.

How to Use

  • Trigger word: Fyre; the author did not specify strength, steps, or CFG.

Risks and Limitations

  • Training images are 20 generated images from Klein 9b; the author notes that examples were not curated, and at least two have anatomical issues.
  • 1 examples are visible, while 10 are hidden; weights are approximately 2.3 GB, much larger than typical character LoRAs.
  • Standard fictional character LoRA with no special capabilities beyond the training configuration.

Trigger Word: Fyre

Listed Only (1)


Data: Civitai public API (base model MiniMax H3), inclusion window 11-14 20:31 → 11-15 09:01 (Beijing Time). Recommendation reasons have been reviewed by editors; download counts only reflect attention levels.

Civitai

Explore the latest AI Radar updates