Skip to content
NewA calmer, faster ZeroHour
StoryModel releaseinfo

Comfy-Org MiniMax H3 Image pack trends at #30 on Hugging Face

1 source · 5 articlesFirst reported Updated ()
What's new

November 8: Comfy-Org’s MiniMax H3 Image ComfyUI pack, with its revenue-restricted license, is the current #30 listing.

Merged summary · x-ai/grok-4.7 · rewritten as coverage arrivesSummaries by Vani AI

Comfy-Org’s MiniMax H3 Image files for ComfyUI remain the latest #30 Hugging Face listing, under a revenue-restricted license.

Comfy-Org published repackaged MiniMax H3 Image files for ComfyUI, and the listing is trending at number 30 on Hugging Face. The pack points to the original MiniMaxAI repository and includes a pruned int8 diffusion model, Qwen3.5 and Qwen3-VL text encoders, and an fp16 VAE. Prompt enhancement is recommended with qwen3.5_9b_w4a8_gptq in the Generate Text node. Text-encoder builds include qwen3vl_32b in int8 and NVFP4 AWQ. A separate MiniMax H3 Image license requires prior written authorization if annualized revenue exceeds 1 million USD or if the user offers hosted services to third parties.

Key facts
  • Listing is trending at number 30 on Hugging Face.
  • Pack includes a pruned int8 diffusion model and an fp16 VAE.
  • Text encoders include Qwen3.5 and Qwen3-VL, including qwen3vl_32b int8 and NVFP4 AWQ.
  • Prompt enhancement is recommended with qwen3.5_9b_w4a8_gptq.
  • Hosted use above 1 million USD annualized revenue needs MiniMax authorization.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

Timeline

dated events in the reporting · oldest first
  1. Nov 8, 2026Comfy-Org MiniMax H3 Image pack reported trending #30 · Hugging Face trending models

What each outlet adds

beyond the shared facts
  • Hugging Face trending modelsLicense threshold, file layout, and recommended prompt-enhancement model
Vendors
MiniMaxComfy-Org
Products
ComfyUIMiniMax H3 Imagegemma-4-31B-it-ARA-heretic-GGUFcactus-compute
Organizations
ConwayResearchnethype GmbHComfy-Org
AI models
Underdog WoofMiniMax-H3-Imageqwen3.5_9b_w4a8_gptqgemma-4-31B-it-ARA-hereticMirageRelayVSR

Coverage

oldest first · one row per article · UTC
  1. · 6d ago Hugging Face trending modelsFirst report

    Comfy-Org repackages RelayVSR weights for ComfyUI

    The Hugging Face card lists int8 diffusion weights and fp32 Flash VAE files for 2x and 4x upscaling, sourced from kopper/RelayVSR.

  2. · 6d ago Hugging Face trending models

    Cactus-Compute releases Mirage vision model on Hugging Face

    Trending at number 30, the repo ships mirage.safetensors and mirage.cact, downloaded on first use.

  3. · 6d ago Hugging Face trending models

    ConwayResearch publishes Underdog Woof, a 40.6 MB English TTS model

    The model card claims 1.42% word error rate for Mira and CPU-only synthesis with numpy.

  4. · 4d ago Hugging Face trending models

    mradermacher publishes GGUF quants of gemma-4-31B-it-ARA-heretic

    Static GGUF files from Q2_K through Q8_0, plus mmproj supplements, are listed as the repo trends at #30.

  5. · 3d ago Hugging Face trending models

    Comfy-Org republishes MiniMax-H3-Image weights for ComfyUI

    The pack adds int8 and NVFP4 files plus Qwen encoders, under a license that restricts high-revenue hosted use.