Wildminder's banner

Wildminder

@wildmindai • 12,346 subscribers

Physicist, Programmer, Designer

Shorts

Qwen-Image-2.1 Consistent Lighting LoRA blends seamlessly object into the scene - no reflections/glares - enhance specular highlights - adds natural shadows

Qwen-Image-2.1 Consistent Lighting LoRA blends seamlessly object into the scene - no reflections/glares - enhance specular highlights - adds natural shadows

155,640 次观看

Qwen-Image 2.1 Seamless Blending LoRA locks subject position and size; tilts background angle to match subject vanishing point; seamless subject-to-background blend.

Qwen-Image 2.1 Seamless Blending LoRA locks subject position and size; tilts background angle to match subject vanishing point; seamless subject-to-background blend.

36,141 次观看

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.

296,991 次观看

Now you can easily make your own perfect clothes‑changing service. Qwen Image 2.1 Outfit Swap Consistency LoRA dresses a person in an outfit from two pics on the original frame; holds 0.1 px from source, no pixel drift

Now you can easily make your own perfect clothes‑changing service. Qwen Image 2.1 Outfit Swap Consistency LoRA dresses a person in an outfit from two pics on the original frame; holds 0.1 px from source, no pixel drift

12,424 次观看

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

23,695 次观看

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 次观看

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.

22,200 次观看

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

17,146 次观看

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.

21,712 次观看

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.

49,541 次观看

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 次观看

is it time to delete DaVinci Resolve?

is it time to delete DaVinci Resolve?

35,069 次观看

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 次观看

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.

14,088 次观看

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 次观看

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 次观看

LTX2.5 Face Swap LoRA

LTX2.5 Face Swap LoRA

11,743 次观看

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 次观看

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.

27,459 次观看

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 次观看

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

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

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

DistScene- turns a single image into an editable 3D scene. Uses sparse voxels, sparse DiT flow-matching models + LoRA. Based on TRELLIS.2 object-centric refinement restores details

DistScene- turns a single image into an editable 3D scene. Uses sparse voxels, sparse DiT flow-matching models + LoRA. Based on TRELLIS.2 object-centric refinement restores details

47,692 次观看 • 11 天前

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

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

366,804 次观看 • 6 个月前

If you own a 3D printer, you need this tool on your radar right now. SNAP3D turns a single 2D image into fully assemblable, multi-part 3D prints with built-in peg-and-socket joints! No glue. No screws. Just print, snap, and build. it cuts the model into semantic parts, optimizes the connectors, and runs physics tests to guarantee stability. Feed it a photo, get real-world snap-fit parts ready for your print bed

If you own a 3D printer, you need this tool on your radar right now. SNAP3D turns a single 2D image into fully assemblable, multi-part 3D prints with built-in peg-and-socket joints! No glue. No screws. Just print, snap, and build. it cuts the model into semantic parts, optimizes the connectors, and runs physics tests to guarantee stability. Feed it a photo, get real-world snap-fit parts ready for your print bed

44,599 次观看 • 1 个月前

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.

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.

248,748 次观看 • 7 个月前

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

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

46,938 次观看 • 1 个月前

Kandinsky 6.0 Video Synchronized audio-video gen. - 5s clips, 44 kHz audio, lip-sync - T2AV, TI2AV - Lite (3B) / Pro (29B) variants - WER 0.124 - up to 1080p via upscaler - fits 16-32GB VRAM - distilled 10-step checkpoints uses Qwen2.5-VL+CLIP.

Kandinsky 6.0 Video Synchronized audio-video gen. - 5s clips, 44 kHz audio, lip-sync - T2AV, TI2AV - Lite (3B) / Pro (29B) variants - WER 0.124 - up to 1080p via upscaler - fits 16-32GB VRAM - distilled 10-step checkpoints uses Qwen2.5-VL+CLIP.

14,581 次观看 • 12 天前

A fast way to turn your phone vids into editable 3D rooms: WorldSculpt. Converts cluttered multi-view video into editable meshes - extracts hundreds of separate object meshes under 75% occlusion - uses Pixal3D + DINOv3 via LoRA - no scene-level training.

A fast way to turn your phone vids into editable 3D rooms: WorldSculpt. Converts cluttered multi-view video into editable meshes - extracts hundreds of separate object meshes under 75% occlusion - uses Pixal3D + DINOv3 via LoRA - no scene-level training.

37,406 次观看 • 1 个月前

Sweet! Marigold V2 is in ComfyUI now. turns regular 2D images into ultra-detailed 3D depth maps. - individual hairs, animal fur, thin foliage - handles surface normals/material properties in a single step - super fast

Sweet! Marigold V2 is in ComfyUI now. turns regular 2D images into ultra-detailed 3D depth maps. - individual hairs, animal fur, thin foliage - handles surface normals/material properties in a single step - super fast

31,853 次观看 • 1 个月前

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.

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.

166,250 次观看 • 8 个月前

Qwen-Image-2.1 Fun Controlnet Union by Alibaba! massive quality-of-life upgrade! one 7.0 GB checkpoint drives 8 controls: - Canny/Depth/Grayscale/HED/Lineart/MLSD/Pose/Scribble - Inpainting - Super fast

Qwen-Image-2.1 Fun Controlnet Union by Alibaba! massive quality-of-life upgrade! one 7.0 GB checkpoint drives 8 controls: - Canny/Depth/Grayscale/HED/Lineart/MLSD/Pose/Scribble - Inpainting - Super fast

19,642 次观看 • 25 天前

Another cool stuff from Alibaba! MiniMax-H3 Acc LoRAs. Parallel Decoding Distillation for efficient video gen in a few steps. FL2VA + Ref2VA

Another cool stuff from Alibaba! MiniMax-H3 Acc LoRAs. Parallel Decoding Distillation for efficient video gen in a few steps. FL2VA + Ref2VA

36,958 次观看 • 1 个月前

MiniMax-H3 360 equirectangular LoRA full-sphere equirectangular video - unwraps 360 with centre forward and edges rear - keeps native H3 audio plays as look-around sphere on Quest/DeoVR/Skybox/YouTube 360.

MiniMax-H3 360 equirectangular LoRA full-sphere equirectangular video - unwraps 360 with centre forward and edges rear - keeps native H3 audio plays as look-around sphere on Quest/DeoVR/Skybox/YouTube 360.

14,353 次观看 • 18 天前

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

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

119,844 次观看 • 10 个月前

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.

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.

112,064 次观看 • 9 个月前

MoGe‑3 is now available in ComfyUI. fine-detail monocular 3D geometry from open-domain images recovers metric point/depth/normal maps + FOV in one pass

MoGe‑3 is now available in ComfyUI. fine-detail monocular 3D geometry from open-domain images recovers metric point/depth/normal maps + FOV in one pass

15,796 次观看 • 1 个月前

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

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

54,296 次观看 • 4 个月前

VideoDeltaNet - near-lossless hybrid attention on MiniMax H3. You can now generate a 14s video faster than you can watch it. - 14.4s 768p clip in 11.23s on 8 B200s - local softmax for detail + linear for long range - streams H3-level video continuously - open weights + inference stack -tops FastH3 quality & instruction-following

VideoDeltaNet - near-lossless hybrid attention on MiniMax H3. You can now generate a 14s video faster than you can watch it. - 14.4s 768p clip in 11.23s on 8 B200s - local softmax for detail + linear for long range - streams H3-level video continuously - open weights + inference stack -tops FastH3 quality & instruction-following

20,821 次观看 • 1 个月前

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.

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.

110,443 次观看 • 11 个月前

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

23,695 次观看 • 1 个月前

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!

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!

22,649 次观看 • 1 个月前