Wildminder's banner
Wildminder's profile picture

Wildminder

@wildmindai • 11,281 subscribers

Physicist, Programmer, Designer

Shorts

MiniMax-H3 Facial Realism CloseUp realism LoRA. Captures subtle textures and micro-expressions - trained on high-quality human-centric portrait - sharp, photorealistic close-ups

MiniMax-H3 Facial Realism CloseUp realism LoRA. Captures subtle textures and micro-expressions - trained on high-quality human-centric portrait - sharp, photorealistic close-ups

15,035 views

HOT! MiniMax-H3 Fun Controlnet Union dropped by Alibaba! all-in-one control for MiniMaxH3 - Canny, Depth, HED, MLSD, Pose - inpainting - single 7GB checkpoint - guidance-distilled for fast 1-pass inference

HOT! MiniMax-H3 Fun Controlnet Union dropped by Alibaba! all-in-one control for MiniMaxH3 - Canny, Depth, HED, MLSD, Pose - inpainting - single 7GB checkpoint - guidance-distilled for fast 1-pass inference

23,080 views

NVIDIA says: no more "brute force every pixel" of video understanding. AutoGaze- identifies and removes redundant video patches before they enter a Vision Transformer. Now we can processes 4K long-video in real-time. Works with SigLIP2 and NVILA.

NVIDIA says: no more "brute force every pixel" of video understanding. AutoGaze- identifies and removes redundant video patches before they enter a Vision Transformer. Now we can processes 4K long-video in real-time. Works with SigLIP2 and NVILA.

296,926 views

Save your money, no more Topaz Starlight. Check this LTX-2.5 Video/Image Enhancer LoRAs. Handles video-image restoration better and faster than commercial tools. Cleans up low-res footage without needing a prompt.

Save your money, no more Topaz Starlight. Check this LTX-2.5 Video/Image Enhancer LoRAs. Handles video-image restoration better and faster than commercial tools. Cleans up low-res footage without needing a prompt.

21,390 views

MiniMax-H3 Turbo LoRA Pruned high-speed audio-video gen. compatibility conversion for pruned/curve-form checkpoints; based on larryvrh’s original weights.

MiniMax-H3 Turbo LoRA Pruned high-speed audio-video gen. compatibility conversion for pruned/curve-form checkpoints; based on larryvrh’s original weights.

28,934 views

MiniMax-H3-TAE by Kijai designed for fast video previews; outperforms standard latent2rgb visualization; requires ComfyUI-KJNodes for integration.

MiniMax-H3-TAE by Kijai designed for fast video previews; outperforms standard latent2rgb visualization; requires ComfyUI-KJNodes for integration.

21,176 views

MiniMax-H3 Anime Line Art Colorization LoRA gens exquisite anime visuals from input line art videos

MiniMax-H3 Anime Line Art Colorization LoRA gens exquisite anime visuals from input line art videos

13,586 views

MiniMax-H3 Realism People LoRA adds real skin texture, micro-expressions, documentary-style motion to videos. Even keeps the audio perfectly synced.

MiniMax-H3 Realism People LoRA adds real skin texture, micro-expressions, documentary-style motion to videos. Even keeps the audio perfectly synced.

13,874 views

LGTM from Apple: 4K feed-forward 3D Gaussian Splatting. instant 4K 3D scenes without massive GPUs.. - predicts a few lightweight 3D shapes, wraps them in ultra-high-res 2D textures. - low Memory usage You take two normal photos of a room. Instantly walk around it in flawless 3D.

LGTM from Apple: 4K feed-forward 3D Gaussian Splatting. instant 4K 3D scenes without massive GPUs.. - predicts a few lightweight 3D shapes, wraps them in ultra-high-res 2D textures. - low Memory usage You take two normal photos of a room. Instantly walk around it in flawless 3D.

46,458 views

Video diffusion models are just overqualified depth estimators! Deterministic single-pass depth estimation based on WanV2.1. - SOTA 5.5 AbsRel on ScanNet - data-efficient than baselines; - no temporal flicker + infinite-length estimation w/ zero scale drift.

Video diffusion models are just overqualified depth estimators! Deterministic single-pass depth estimation based on WanV2.1. - SOTA 5.5 AbsRel on ScanNet - data-efficient than baselines; - no temporal flicker + infinite-length estimation w/ zero scale drift.

49,491 views

is it time to delete DaVinci Resolve?

is it time to delete DaVinci Resolve?

35,069 views

CogOmniControl by Tencent. Reasoning-driven controllable video gen. CogVLM + CogOmniDiT to translate sparse storyboards/sketches into production-quality video. beats VINO, VACE-Wan2.1

CogOmniControl by Tencent. Reasoning-driven controllable video gen. CogVLM + CogOmniDiT to translate sparse storyboards/sketches into production-quality video. beats VINO, VACE-Wan2.1

24,123 views

LTX2.3 ReStyle LoRA Transfers simpler styles (flat 2D, cel-shaded, monochrome line art). struggles with complex styles (texture, intricate detail, strong material/lighting effects).

LTX2.3 ReStyle LoRA Transfers simpler styles (flat 2D, cel-shaded, monochrome line art). struggles with complex styles (texture, intricate detail, strong material/lighting effects).

24,442 views

ComfyUI-WanVideoWrapper now supports SteadyDancer: like WanAnimate - human image animation framework; produces high-fidelity, coherent motion

ComfyUI-WanVideoWrapper now supports SteadyDancer: like WanAnimate - human image animation framework; produces high-fidelity, coherent motion

42,246 views

3D modeling entirely replaced by stick figures. SK-Adapter brings skeleton-based structural control for native 3D. > Feed it a basic skeleton > Type what you want to see > Get a fully rendered 3D character in under 15 seconds > Already rigged and ready for animation > Zero Blender experience required Game devs are happy.

3D modeling entirely replaced by stick figures. SK-Adapter brings skeleton-based structural control for native 3D. > Feed it a basic skeleton > Type what you want to see > Get a fully rendered 3D character in under 15 seconds > Already rigged and ready for animation > Zero Blender experience required Game devs are happy.

26,931 views

Klein 9B Sun Direction LoRA Nice LoRA that lets you move the sun to a specific spot in the sky just by pointing at a reference ball.

Klein 9B Sun Direction LoRA Nice LoRA that lets you move the sun to a specific spot in the sky just by pointing at a reference ball.

11,580 views

Photos to 3D model with 2Xplat. Pose-free 3D Gaussian Splatting - 0.15s–0.31s inference; - beats YoNoSplat; - high-fidelity splats

Photos to 3D model with 2Xplat. Pose-free 3D Gaussian Splatting - 0.15s–0.31s inference; - beats YoNoSplat; - high-fidelity splats

23,504 views

LightVAE + ComfyUI node: High-performance video VAE; runs 2–3x faster using 50% less memory; LightTAE offers a 10+x speedup on just ~0.4GB VRAM

LightVAE + ComfyUI node: High-performance video VAE; runs 2–3x faster using 50% less memory; LightTAE offers a 10+x speedup on just ~0.4GB VRAM

38,092 views

Thanks to Kijai, One-to-All Animation has already been added to ComfyUI.

Thanks to Kijai, One-to-All Animation has already been added to ComfyUI.

33,914 views

Unsloth dropped new LTX-2.3 GGUFs. > Dev/distilled UD-Q2/Q5

Unsloth dropped new LTX-2.3 GGUFs. > Dev/distilled UD-Q2/Q5

24,502 views

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

Lucida from ByteDance Cool project! It transforms indoor video into editable 3D scenes; reconstructs objects as simulation-ready assets - VLM-based object detection and referring descriptions. - good at pose alignment - high-fidelity real-to-sim digital twins. - multi-view masks, boxes, partial point clouds - Seed3D 2.0 for image-to-3D asset gen
0:38
wildmindai's profile picture

Lucida from ByteDance Cool project! It transforms indoor video into editable 3D scenes; reconstructs objects as simulation-ready assets - VLM-based object detection and referring descriptions. - good at pose alignment - high-fidelity real-to-sim digital twins. - multi-view masks, boxes, partial point clouds - Seed3D 2.0 for image-to-3D asset gen

Wildminder

44,774 views • 2 days ago

Hot drop! Forget paid TTS like ElevenLabs for interactive AI voices. > Meet Breeze TTS 2! design any voice, direct every performance in real time. - tops Voice Design bench - fastest time-to-first-audio - character creation - high speaker similarity across 16 languages. Amazing audio quality! It runs on consumer GPUs!
0:33
wildmindai's profile picture

Hot drop! Forget paid TTS like ElevenLabs for interactive AI voices. > Meet Breeze TTS 2! design any voice, direct every performance in real time. - tops Voice Design bench - fastest time-to-first-audio - character creation - high speaker similarity across 16 languages. Amazing audio quality! It runs on consumer GPUs!

Wildminder

22,649 views • 8 days ago

Netflix dropped some useful stuff. VOID -video object and interaction deletion. - removes objects while realistically simulating physical consequences; - beats Runway/ProPainter; - CogVideoX-5B + SAM 2; looks good, no smudges/artifacts
0:41
wildmindai's profile picture

Netflix dropped some useful stuff. VOID -video object and interaction deletion. - removes objects while realistically simulating physical consequences; - beats Runway/ProPainter; - CogVideoX-5B + SAM 2; looks good, no smudges/artifacts

Wildminder

366,147 views • 5 months ago

HOT! MiniMax-H3 Fun Controlnet Union dropped by Alibaba! all-in-one control for MiniMaxH3 - Canny, Depth, HED, MLSD, Pose - inpainting - single 7GB checkpoint - guidance-distilled for fast 1-pass inference
0:05
wildmindai's profile picture

HOT! MiniMax-H3 Fun Controlnet Union dropped by Alibaba! all-in-one control for MiniMaxH3 - Canny, Depth, HED, MLSD, Pose - inpainting - single 7GB checkpoint - guidance-distilled for fast 1-pass inference

Wildminder

23,080 views • 10 days ago

llmfit. Useful tool that probes hardware and tells you exactly which LLMs will actually run. - handles MoE expert offloading, picks the best quantization for your RAM, estimates tokens/sec before you even pull the weights. Essential for local dev.
0:22
wildmindai's profile picture

llmfit. Useful tool that probes hardware and tells you exactly which LLMs will actually run. - handles MoE expert offloading, picks the best quantization for your RAM, estimates tokens/sec before you even pull the weights. Essential for local dev.

Wildminder

248,279 views • 6 months ago

ComfyUI MiniMax-H3 Audio Refine audio-only refinement. Makes high-quality audio on 4-step Turbo video by running extra denoising steps on the audio stream only - preserves video
0:30
wildmindai's profile picture

ComfyUI MiniMax-H3 Audio Refine audio-only refinement. Makes high-quality audio on 4-step Turbo video by running extra denoising steps on the audio stream only - preserves video

Wildminder

15,139 views • 12 days ago

A totally new level of pose control in ComfyUI - VNCCS. - full 3D Pose Studio for character posing & lighting, - multi-pose, body generator, pose gallery; - vision-guided QWEN Detailer + camera controls.
1:04
wildmindai's profile picture

A totally new level of pose control in ComfyUI - VNCCS. - full 3D Pose Studio for character posing & lighting, - multi-pose, body generator, pose gallery; - vision-guided QWEN Detailer + camera controls.

Wildminder

165,539 views • 7 months ago

MiniMax-H3 4-Step Turbo LoRA by joyfox. - T2V, I2V - Joint audio-video velocity prediction correction for synchronized outputs - Optimized for the fl2va pruned bf16 base
0:30
wildmindai's profile picture

MiniMax-H3 4-Step Turbo LoRA by joyfox. - T2V, I2V - Joint audio-video velocity prediction correction for synchronized outputs - Optimized for the fl2va pruned bf16 base

Wildminder

18,806 views • 24 days ago

It's a real beast! Qwen3.8 is going to make a lot of web designers and frontend devs quit. One-shot a full-featured Vue.js proxy/VPN dashboard in 20 minutes: - nice design - smooth animations - works out of the box, no errors
1:06
wildmindai's profile picture

It's a real beast! Qwen3.8 is going to make a lot of web designers and frontend devs quit. One-shot a full-featured Vue.js proxy/VPN dashboard in 20 minutes: - nice design - smooth animations - works out of the box, no errors

Wildminder

30,584 views • 1 month ago

Sweet. RAVEN - turns MiniMax‑H3 into a real-time video streaming engine. It streams video chunk by chunk like a livestream, no drift, no glitches even on long runs.
0:32
wildmindai's profile picture

Sweet. RAVEN - turns MiniMax‑H3 into a real-time video streaming engine. It streams video chunk by chunk like a livestream, no drift, no glitches even on long runs.

Wildminder

11,882 views • 15 days ago

Sweet! Kijai has added standalone ComfyUI nodes for SCAIL pose processing.
0:24
wildmindai's profile picture

Sweet! Kijai has added standalone ComfyUI nodes for SCAIL pose processing.

Wildminder

119,844 views • 8 months ago

HOT! SCAIL-2 just dropped! End-to-end character animation via in-context conditioning - no skeleton middleman, it copies pixels directly - no glitches, no messy hands - 512p/704p - unified architecture for character replacement and multi-character tasks. - zero-shot generalization to animal-driven and mesh-based control.
0:37
wildmindai's profile picture

HOT! SCAIL-2 just dropped! End-to-end character animation via in-context conditioning - no skeleton middleman, it copies pixels directly - no glitches, no messy hands - 512p/704p - unified architecture for character replacement and multi-character tasks. - zero-shot generalization to animal-driven and mesh-based control.

Wildminder

46,070 views • 2 months ago

Soprano: An instant, ultra-lightweight TTS model for realistic speech; generates 10 hours of 32kHz audio in <20s; streams with <15ms latency using just 80M params & <1GB VRAM. Has some limitations and drawbacks.
0:37
wildmindai's profile picture

Soprano: An instant, ultra-lightweight TTS model for realistic speech; generates 10 hours of 32kHz audio in <20s; streams with <15ms latency using just 80M params & <1GB VRAM. Has some limitations and drawbacks.

Wildminder

111,995 views • 8 months ago

Hunyuan3D-Buffalo 1.0 - unified foundation for 3D generation, understanding, and editing You can swap or remove parts with simple commands while keeping the original geometry intact. - Qwen-VL+TRELLIS+Hunyuan3D - Trained on 87M samples
0:25
wildmindai's profile picture

Hunyuan3D-Buffalo 1.0 - unified foundation for 3D generation, understanding, and editing You can swap or remove parts with simple commands while keeping the original geometry intact. - Qwen-VL+TRELLIS+Hunyuan3D - Trained on 87M samples

Wildminder

18,174 views • 29 days ago

LTX2.3 Obscura Remove LoRA. Some kind of a "digital X-ray" for video cleanup. - Strips foreground junk. Peel back smoke, haze, or clutter - Reconstructs hidden scenes. Describe the background to fill holes.
0:23
wildmindai's profile picture

LTX2.3 Obscura Remove LoRA. Some kind of a "digital X-ray" for video cleanup. - Strips foreground junk. Peel back smoke, haze, or clutter - Reconstructs hidden scenes. Describe the background to fill holes.

Wildminder

56,369 views • 4 months ago

JoyAI-Echo + LTX-2.3 merge. kills character drift and robotic audio. It grafts Echo’s identity memory onto LTX’s natural voice. You get one consistent character with human-grade narration across every shot in your sequence.
0:30
wildmindai's profile picture

JoyAI-Echo + LTX-2.3 merge. kills character drift and robotic audio. It grafts Echo’s identity memory onto LTX’s natural voice. You get one consistent character with human-grade narration across every shot in your sequence.

Wildminder

22,772 views • 1 month ago

CS:GO + Adobe + Wan2.1 = WorldCam. Interactive autoregressive 3D gaming worlds. > AI now generates playable 3D worlds live > You move the mouse, the AI builds the map instantly > Turn around, and it remembers exactly what was there No traditional game engines. Just neural networks hallucinating reality.
0:40
wildmindai's profile picture

CS:GO + Adobe + Wan2.1 = WorldCam. Interactive autoregressive 3D gaming worlds. > AI now generates playable 3D worlds live > You move the mouse, the AI builds the map instantly > Turn around, and it remembers exactly what was there No traditional game engines. Just neural networks hallucinating reality.

Wildminder

67,824 views • 5 months ago

No way. Adobe's new node editor is a straight-up ComfyUI clone! The killer feature is encapsulating an entire graph into a simple tool that can be dropped into Photoshop.
0:21
wildmindai's profile picture

No way. Adobe's new node editor is a straight-up ComfyUI clone! The killer feature is encapsulating an entire graph into a simple tool that can be dropped into Photoshop.

Wildminder

110,443 views • 10 months ago

LTX2.3 Black Magic LoRA. transforms dark/underexposed footage into visually rich scenes - preserves composition/motion while imagining plausible details; built for creative VFX and night shots, not for forensic recovery
0:33
wildmindai's profile picture

LTX2.3 Black Magic LoRA. transforms dark/underexposed footage into visually rich scenes - preserves composition/motion while imagining plausible details; built for creative VFX and night shots, not for forensic recovery

Wildminder

17,788 views • 1 month ago

SUPIR upscaler is outdated. ASASR- turns blurry, low-quality photos into sharp, high-res images. Prevents the fake hallucinated details. - improves OCR - high segmentation accuracy - based on FLUX.1 dev this looks sweet
0:48
wildmindai's profile picture

SUPIR upscaler is outdated. ASASR- turns blurry, low-quality photos into sharp, high-res images. Prevents the fake hallucinated details. - improves OCR - high segmentation accuracy - based on FLUX.1 dev this looks sweet

Wildminder

41,951 views • 3 months ago