Fibo 2.0 Edit in 2 Steps: New IDM LoRA + Demo
A community IDM LoRA halves Bria's Fibo 2.0 Edit Turbo from four steps to two, with no CFG. The final adapter and a free Hugging Face demo are live now.
Dispatches
Generative AI: Reports · Model Drops · Prompts · Tutorials
Spotlight
Advertisement
H3 Continuity: ComfyUI Shots That Remember the Room
A new open-source ComfyUI node pack gives MiniMax H3 a timeline with visual memory. Walk out of a room, cut back in from another angle, and the sofa, cat and teapot are still where you left them.
Anima RGBA: Real Transparent PNGs From Anima
A new open RGBA VAE plus LoRA lets the Anima anime model output true alpha-channel PNGs in stock ComfyUI. Swap the VAE, add one LoRA and type "transparent background" for clean cut-outs with no background remover.
LTX-2.5 Video With Sound, Locally on Any Mac
A new one-paste installer runs Lightricks' open LTX-2.5 22B distilled model on Macs, Intel CPUs included. Patched GGUF loaders with Metal kernels stream the model from disk, so a 2-second clip with sound takes about 20 minutes on an 8 GB machine.
Silencio-2: 18M CPU TTS With Emotion Tags
BlueRose Labs fine-tuned Kyutai's Pocket TTS 18M into Silencio-2, a CC-BY-4.0 English voice model that takes inline tags like [sigh], [laugh] and whisper cues, clones a voice from a short clip, and runs about 20x faster than real time on a plain CPU.
MiniMax H3 on an AMD RX 6900 XT, 20x Faster
A new open toolkit runs MiniMax H3 video with audio on a 16 GB AMD RX 6900 XT under Windows through stable-diffusion.cpp and ROCm. Tuning cut one 480p clip from 62 minutes to about 3, and every fix is documented.
MOSS-Image Hits 2 Steps With an Open IDM Adapter
A community LoRA trained with inclusionAI's new Intrinsic Distribution Matching recipe gets MOSS-Image down to 2 steps with no CFG. That's 2 DiT passes instead of 100, with a free Space and a ComfyUI path you can use today.
Krea 2 BBOX Turbo Goes INT8 for Boxed Comic Layouts
A community Krea 2 fine-tune that places panels, characters and exact speech-bubble text inside boxes you draw in plain text just got INT8 builds. That's about 14 GB instead of 26 GB, and they drop straight into ComfyUI's stock Krea 2 template.
LUMEN Turns Photos Into HDR Lighting With a FLUX LoRA
A SIGGRAPH Asia 2026 paper just shipped code and a 717 MB FLUX.1-dev LoRA that turns ordinary photos into full 360° HDR environment maps. It can even give you a different light probe for every spot in a room.
H3 LowVRAM Squeezes MiniMax H3 Onto 8 GB GPUs
A new experimental launcher for native ComfyUI splits MiniMax H3's attention and MLP work into 1024-token chunks. On an 8 GB laptop RTX 5060, a 10-second 768×1344 clip with audio stopped running out of memory.
AI Media Router: One MCP for 43 Image and Video APIs
Jutsu Studio's new open-source MCP server lets Claude, Cursor or Codex price-shop Seedance, Kling, Veo, FLUX and friends across 43 providers (or your own ComfyUI), stop at a budget, and keep every result in a local library.
Any-to-Bokeh Brings Video Rack Focus to ComfyUI
A new unofficial ComfyUI pack wraps vivo's ICLR 2026 Any-to-Bokeh model, so you can script a cinematic focus pull onto finished footage, keyframe by keyframe, without regenerating a single frame.
FaceTrue Restore Fixes Old Video Faces With One Photo
A new open-weights ComfyUI app hands LTX-2.5's Restore IC-LoRA one clear photo of the person, then shows you side by side how much that photo pulls a blurry home-video face back toward the real one.
Detail Fixer Repairs Logos, Faces and Hands in ComfyUI
A new MIT node pack finds garbled logos, odd faces and broken hands with SAM 3 and regenerates only those patches. It uses local Qwen Image Edit on a 10 GB GPU, or Nano Banana 2 and GPT Image 2 via partner nodes, and blends the result back pixel-perfect.
ComfyUI-Ardy Steers NVIDIA ARDY Motion Into H3
A new MIT node pack brings NVIDIA's SIGGRAPH 2026 ARDY motion model into ComfyUI. You click the ground to steer a live 3D body, record the take, and render it as driving frames for MiniMax H3 or as a GLB.
ComfyUI Saves ProRes 4444 Video, Alpha Included
ComfyUI core now writes ProRes straight from Save Video, as 10-bit 4444 with alpha or 422 HQ in MOV or MKV, and adds a chroma-subsampling switch to Create Video. It was merged on November 1, so git users can pull it today.
ChronoEdit-14B Goes 4-Step With a New DMD Distill
A new Apache-2.0 DMD distill of NVIDIA's ChronoEdit-14B edits images in 4 network evaluations instead of 100, and it matches the 50-step model on GEdit-Bench. It went up on Hugging Face on November 1.
H3MD Director: 2-Minute MiniMax H3 Videos in ComfyUI
H3MD Director is a new open-source ComfyUI node pack that plans multi-shot MiniMax H3 videos, renders them segment by segment to 2+ minutes at 1080p, and re-renders only the bad segments. It went live on the Comfy Registry on October 31.
Chroma-H3: Lodestone Turns MiniMax H3 Into a Stills Model
Lodestone's chroma-h3 fine-tunes the MiniMax H3 video model into a text-to-image stills model, with open weights, a rank-256 LoRA and a new 8-step DMD LoRA. A ComfyUI-format conversion is already up on Hugging Face.
Ultra Elements: 39 Open-Source three.js Spell Effects, Built by AI Agents One Element at a Time
Ian's MIT-licensed Ultra Elements packs 39 real-time spell effects for the browser, from fireballs to portals, and its plan shows how parallel AI agents built each element under a 3 ms frame budget.
Categories
ArtRealmAI Gen
-
Now
Reference to video
MiniMax H3 Max and Seedance 2.0 Fast take up to 9 images. Cite them as Picture or @Image tags. First 4 H3 images are included; each extra is 3¢. Seedance images are included in the per-second rate.
-
Video
Flux 3 video
Text or image to video, draft or full, 5–20 seconds with audio. Grok and MiniMax are still on the rail.
-
Outpost
Share with the realm
Pin favorite gens to your public profile. Load a prompt back into Gen.
-
Tools
Logo Layer
Stamp a logo on a folder of images or videos in the browser.
-
Free
Klein 9B daily
4 free stills a day on Flux.2 Klein 9B after you sign in (4 at 1K or 2 at 2K).