Wildminder

@wildmindai

Physicist, Programmer, Designer

Berlin

Wildminder
@wildmindai
6h
MiniMax-H3-Image Prompt Expansion GGUF. fine-tuned from Qwen3.8-27B, FP4 - short requests -> detailed captions + aspect ratios - thinking on by default - needs 19GB GPU huggingface.co/prithivMLmods/…
Wildminder
@wildmindai
6h
This is nuts! That cool MiniMax-H3-Image model already has a 2-step LoRA! - rank-128 - 1.4x faster than stock 6-step - realtime ~1 MP previews in 1–1.5 s! huggingface.co/akhaliq/minima…
MiniMax (official)
@MiniMax_AI
12h
00:50
4K image generation in 10 seconds! ⚡ Meet MiniMax H3-Image. 16 million pixel resolution. Stunning realism. Precise prompt following & editing. Up to 16 reference images. All in 10 seconds. And it's open-weight. 🚀 Available now via our API, MiniMax Code, and Hailuo AI — with
6
Wildminder
@wildmindai
16h
MOSS-Image Base DMD2 8-step LoRA huggingface.co/data-archetype…
Wildminder
@wildmindai
17h
Minimax-H3-Image-Restyle Content-Preserving Style Transfer. Updated, new 1000s LoRA huggingface.co/witcherderivia…
3
Wildminder
@wildmindai
Nov 9
Tencent’s cool new WeVisOne-VL is now supported in ComfyUI! all-in-one VL model that unifies - object detection - referring localization - counting, pointing - OCR - segmentation + alpha matting The 4B model in INT8 is just 5 GB! huggingface.co/Comfy-Org/WeVi…
2

Wildminder’s posts