@ComfyUI #OpenSourceHiggsfield# Submission: Instead of 1 feature, we built the entire Higgsfield platform + way more... but open source. 🎬 Imagination Studio. An all in one studio with 61+ apps. Video,Music,Audio, Sfx/Foley, Agents, Prompt Assistance, Depth Mapping, Audio Separation, Loras, Custom 3D animatics, Editing. Collab by Me and @u1tra_instinct REPO LINK BELOW: 👇

Big Announcement: Meet Imagination Studio🎬🎵 by @u1tra_instinct and Me! Our local open source all in one creative platform on your own hardware has been fully redesigned and rebuilt from the ground up. Video,Audio, Music, Image. Releasing ASAP with latest+best local models.

New Release: Wasserman's 80s Horror Lora My free LoRA for MiniMax H3. One trigger word and your scene looks like a 1984 rental: VHS or grindhouse 16mm for 70s style. One-line ComfyUI install. Be kind, rewind. 🤡🔪📼 Repo here👇 What you get: 🎞️ VHS or 16mm from one trigger word 🧛 Your scene stays your scene. It changes the look, not the story 🔊 Trained with audio, so the screams, dialogue and creaky floorboards still hit 🧩 Plug-and-play ComfyUI workflows: text-to-video and image-to-video ⚡ A one-line installer that finds ComfyUI, drops in the LoRA and loads the workflows 🩸 Works with standard or uncensored H3 (uncensored hits hardest) I trained it on 48 horror shots I made over the course of a few weeks. If you saw my horror montages, this is trained on those.

Friday Fun Video: Everyone’s talking about JEV. Where did he come from? How did he blow up overnight? What’s his backstory? I did some deeply unqualified investigative journalism and may have found the OG JEV. This you Jev?👇 @CompleteSkeptic :).

Almost nobody pays for AI out of pocket yet Only ~3% of US consumers do, up from under 1% in 2023 The youngest buyers are adopting at 4x the rate of the oldest Charts of the Week:

Who will be at @capcutapp World Los Angeles event on October 24th? I'll be there, would love to catch up and hang if you're there. Let me know. Will be great to get together with so many other awesome filmmakers/creators in this space.

If you missed the X spaces I was a guest on earlier, here is a link to the recording below from “We the Film3” where I discussed so much that I love - filmmaking, tech, Ai, process etc. Take a listen if you can. It was a great chat.

Three paths to faster video attention: compute the same interactions more efficiently, compute fewer in full, or change how information is mixed. Here’s a visual guide. 👇 Thanks to Nunchux AI and collaborators for VC-Attention, bringing training-free low-bit acceleration to MiniMax-H3, with better fidelity than SageAttention2 in the B200 evaluation. The approach balances speed and fidelity: V-Smooth reduces value quantization error, while ExpCast-FP8 makes softmax faster through approximation. Excited to see the community keep building on H3. Could combining low-bit computation with sparse methods like Sol-Attn push efficiency further? We’re looking forward to seeing that explored.

So cool finally got my @autonomous_labs harness device setup and connected to 14 agents across multiple computers, harnesses, models etc. This device is great. Well done @dee_hw