Loading video...

Video Failed to Load

Go Home

Elevate your ComfyUI video outputs this fall. ๐Ÿš€ Launching with RTX Spark, RTX Video Frame Generation arrives as a ComfyUI node and Python wheel. Multiply frame rates to turn choppy 15-20 fps outputs into smooth, high-quality playback.

NVIDIARTXSpark's profile picture

NVIDIA RTX Spark

55,762 subscribers

69,808 views โ€ข 4 months ago โ€ขvia X (Twitter)

Science & Technology
LIVE

Anya Rossiโ€ข Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Turn a simple idea into a storyboard, then generate the video with Seedance 2.0. This ComfyUI workflow uses LLMs to structure prompts into storyboard-ready scenes that define how the video should play out. The storyboard can be paired with reference images and sent directly into Seedance for video generation. To try this workflow, link below ๐Ÿ‘‡
0:12

Turn a simple idea into a storyboard, then generate the video with Seedance 2.0. This ComfyUI workflow uses LLMs to structure prompts into storyboard-ready scenes that define how the video should play out. The storyboard can be paired with reference images and sent directly into Seedance for video generation. To try this workflow, link below ๐Ÿ‘‡

ComfyUI

33,988 views โ€ข 4 months ago

Real Human support for Seedance 2.0 is now available in ComfyUI. Unlock real human video generation with Seedance 2.0 now in ComfyUI. This unlocks real-person video generation with consistent identity and authentic facial expressions โ€” after a one-time verification.
0:14

Real Human support for Seedance 2.0 is now available in ComfyUI. Unlock real human video generation with Seedance 2.0 now in ComfyUI. This unlocks real-person video generation with consistent identity and authentic facial expressions โ€” after a one-time verification.

ComfyUI

48,571 views โ€ข 6 months ago

MiniMax H3 just got 9ร— faster On an RTX 4090. Locally video generation shrink down From 11 minutes to 72 seconds on 16 GB GPUs Open-source New ComfyUI node drops MiniMax H3 character video generation 9ร— faster. How? ComfyUI-Ref2VA-VSA uses sparse attention DiT to deliver: - 72s for a full 5s video 24fps (124 frames) - 13.5 GB peak VRAM (runs cleanly on 16 GB GPUs) - 4-step sampling with 75% sparsity - Zero face drift character identity stays locked - Native H3: 650s - Video Delta Net: 135s - Ref2VA VSA: 72s This is the closest thing to real-time character video generation weโ€™ve seen in ComfyUI. -
0:10

MiniMax H3 just got 9ร— faster On an RTX 4090. Locally video generation shrink down From 11 minutes to 72 seconds on 16 GB GPUs Open-source New ComfyUI node drops MiniMax H3 character video generation 9ร— faster. How? ComfyUI-Ref2VA-VSA uses sparse attention DiT to deliver: - 72s for a full 5s video 24fps (124 frames) - 13.5 GB peak VRAM (runs cleanly on 16 GB GPUs) - 4-step sampling with 75% sparsity - Zero face drift character identity stays locked - Native H3: 650s - Video Delta Net: 135s - Ref2VA VSA: 72s This is the closest thing to real-time character video generation weโ€™ve seen in ComfyUI. -

Md Ismail ล ojal๎จ€ ๐Ÿ•ท๏ธ

64,917 views โ€ข 17 days ago

Another local video created with MiniMax H3 on DGX Spark, it took forever 1 hours and 20 minutes ๐Ÿ˜ฑ For: - 1280x736 (16:9) - 15 seconds - DGX Spark - ComfyUI Template Text to Video Thanks MiniMax (official) for this model!
0:15

Another local video created with MiniMax H3 on DGX Spark, it took forever 1 hours and 20 minutes ๐Ÿ˜ฑ For: - 1280x736 (16:9) - 15 seconds - DGX Spark - ComfyUI Template Text to Video Thanks MiniMax (official) for this model!

Ivan Fioravanti

40,984 views โ€ข 3 months ago

NVIDIA says DLSS 5 is getting a big performance boost. The new AI model is twice as fast as the September version and uses 20% less VRAM at 4K, while keeping similar image quality. Hereโ€™s whatโ€™s coming: >Hogwarts Legacy: DLSS 5 arrives on November 5. >Where Winds Meet: DLSS 5 is coming in a future update. >NBA 2K27: Gets the new model on October 16, with up to 1.4x higher frame rates. >Frame Generation: A new experimental mode can boost performance by up to 35% on an RTX 5060, with a small drop in image quality. >RTX Remix: Gets the updated technology on October 23, giving modders more ways to improve the graphics of older games.
0:16

NVIDIA says DLSS 5 is getting a big performance boost. The new AI model is twice as fast as the September version and uses 20% less VRAM at 4K, while keeping similar image quality. Hereโ€™s whatโ€™s coming: >Hogwarts Legacy: DLSS 5 arrives on November 5. >Where Winds Meet: DLSS 5 is coming in a future update. >NBA 2K27: Gets the new model on October 16, with up to 1.4x higher frame rates. >Frame Generation: A new experimental mode can boost performance by up to 35% on an RTX 5060, with a small drop in image quality. >RTX Remix: Gets the updated technology on October 23, giving modders more ways to improve the graphics of older games.

Pirat_Nation ๐Ÿ”ด

90,691 views โ€ข 20 days ago

Shoutout to the Kling AI team! 4 fantastic image and video generation features are now available in ComfyUI!:
0:15

Shoutout to the Kling AI team! 4 fantastic image and video generation features are now available in ComfyUI!:

ComfyUI

36,143 views โ€ข 1 year ago

๏ผˆ*ใ‚œใƒผใ‚œ*๏ผ‰ Sound On Please! ComfyUI workflow for turning SDXL Turbo outputs into a video! Pass it folder of SDXL Turbo frames or any folder of frames. This piece is called: 'God of Time' Audio by me as well. Workflow here:
0:20

๏ผˆ*ใ‚œใƒผใ‚œ*๏ผ‰ Sound On Please! ComfyUI workflow for turning SDXL Turbo outputs into a video! Pass it folder of SDXL Turbo frames or any folder of frames. This piece is called: 'God of Time' Audio by me as well. Workflow here:

็„ก้™ ๐Ÿ’€ acc/acc

15,223 views โ€ข 2 years ago

Seedance 2.0 is now available in 1080p. Higher resolution. Sharper outputs. Run it ๐Ÿ‘‡
0:13

Seedance 2.0 is now available in 1080p. Higher resolution. Sharper outputs. Run it ๐Ÿ‘‡

ComfyUI

17,914 views โ€ข 6 months ago

Create a storyboard, feed it into Seedance 2.0, and let an LLM analyze the storyboard to generate better prompts. A practical way to turn visual planning into more controlled and consistent video generation. To try this workflow, link below ๐Ÿ‘‡
0:11

Create a storyboard, feed it into Seedance 2.0, and let an LLM analyze the storyboard to generate better prompts. A practical way to turn visual planning into more controlled and consistent video generation. To try this workflow, link below ๐Ÿ‘‡

ComfyUI

35,014 views โ€ข 4 months ago

Ready to get started with visual generative AI? Look no further. Learn how to run image and video models locally on RTX GPUs using ComfyUI with LTX & BlackForestLabsAI - Unofficial FLUX in our blog below. ๐Ÿ‘‡
0:10

Ready to get started with visual generative AI? Look no further. Learn how to run image and video models locally on RTX GPUs using ComfyUI with LTX & BlackForestLabsAI - Unofficial FLUX in our blog below. ๐Ÿ‘‡

NVIDIA RTX Spark

1,270,333 views โ€ข 9 months ago

Creator seungho__yeo ( IG ) built a morphing transition workflow on ComfyUI Cloud + Seedance 2 โ†’ seamless frame blending โ†’ character consistency preserved โ†’ cinematic This is pretty sick! ๐Ÿ”ฅ
0:15

Creator seungho__yeo ( IG ) built a morphing transition workflow on ComfyUI Cloud + Seedance 2 โ†’ seamless frame blending โ†’ character consistency preserved โ†’ cinematic This is pretty sick! ๐Ÿ”ฅ

ComfyUI

12,423 views โ€ข 4 months ago

Seedance 2.0 is now live in ComfyUI for everyone. This state-of-the-art model brings us one step closer to production-quality video generations.
0:17

Seedance 2.0 is now live in ComfyUI for everyone. This state-of-the-art model brings us one step closer to production-quality video generations.

ComfyUI

63,184 views โ€ข 6 months ago

Our first #GeForceRTX50 spotlight: GeForce RTX 5090 Founders Edition โšซ DLSS 4 with Multi Frame Gen โšซ Ultimate responsiveness with Reflex 2 โšซ Double Flow Through design Want to WIN the next generation of RTX? Comment #GeForceRTX50 Good luck!
0:11

Our first #GeForceRTX50 spotlight: GeForce RTX 5090 Founders Edition โšซ DLSS 4 with Multi Frame Gen โšซ Ultimate responsiveness with Reflex 2 โšซ Double Flow Through design Want to WIN the next generation of RTX? Comment #GeForceRTX50 Good luck!

NVIDIA GeForce

1,849,219 views โ€ข 1 year ago

๐ŸงฎTurn single image into a custom LoRA model in one click ! Should work for character and product ! This ComfyUI workflow: โ†’ Uses Gemini AI to generate 20 diverse prompts from your image โ†’ Creates 20 consistent variations with FLUX.1 Kontext โ†’ Automatically builds the dataset + trains the LoRA One image in โ†’ Trained LoRA out ๐ŸŽฏ #ComfyUI #LoRA #AIArt #FLUX #AutomatedAI ComfyUI BlackForestLabsAI - Unofficial ๐Ÿ”— Check it out: This workflow was made for the hackathon organized by ComfyUI in SF yesterday
0:15

๐ŸงฎTurn single image into a custom LoRA model in one click ! Should work for character and product ! This ComfyUI workflow: โ†’ Uses Gemini AI to generate 20 diverse prompts from your image โ†’ Creates 20 consistent variations with FLUX.1 Kontext โ†’ Automatically builds the dataset + trains the LoRA One image in โ†’ Trained LoRA out ๐ŸŽฏ #ComfyUI #LoRA #AIArt #FLUX #AutomatedAI ComfyUI BlackForestLabsAI - Unofficial ๐Ÿ”— Check it out: This workflow was made for the hackathon organized by ComfyUI in SF yesterday

Lovis Odin

69,609 views โ€ข 1 year ago

basically, you can generate this level quality of Ai-video locally on RTX 3090 MiniMax H3 runs on your own hardware for text-to-video, image-to-video, and reference-to-video with native stereo audio.
0:15

basically, you can generate this level quality of Ai-video locally on RTX 3090 MiniMax H3 runs on your own hardware for text-to-video, image-to-video, and reference-to-video with native stereo audio.

Md Ismail ล ojal๎จ€ ๐Ÿ•ท๏ธ

57,349 views โ€ข 2 months ago

LightVAE + ComfyUI node: High-performance video VAE; runs 2โ€“3x faster using 50% less memory; LightTAE offers a 10+x speedup on just ~0.4GB VRAM
0:15

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

Wildminder

38,092 views โ€ข 1 year ago

MiniMax H3 โšก๏ธ Spectrum acceleration in ComfyUI โ€” 34% lower Euler sampling time, 30% lower RES time Tested at approximately 0.5 MP, 8 seconds and 20 steps on an RTX PRO 6000 under WSL, using High VRAM mode ๐Ÿ‘‡
0:10

MiniMax H3 โšก๏ธ Spectrum acceleration in ComfyUI โ€” 34% lower Euler sampling time, 30% lower RES time Tested at approximately 0.5 MP, 8 seconds and 20 steps on an RTX PRO 6000 under WSL, using High VRAM mode ๐Ÿ‘‡

Stable Diffusion Tutorials

29,096 views โ€ข 3 months ago

Introducing Reflex 2 with Frame Warp, the next innovation in lowering latency and increasing responsiveness. Coming soon for all GeForce RTX users, releasing first on RTX 50 Series GPUs โ†’
0:18

Introducing Reflex 2 with Frame Warp, the next innovation in lowering latency and increasing responsiveness. Coming soon for all GeForce RTX users, releasing first on RTX 50 Series GPUs โ†’

NVIDIA GeForce

528,423 views โ€ข 1 year ago

๐ŸŽ‰ The built-in node help menu is now available to everyone. ๐Ÿ” Just update your ComfyUI to the latest version and make sure the frontend is at least v1.22.2
0:19

๐ŸŽ‰ The built-in node help menu is now available to everyone. ๐Ÿ” Just update your ComfyUI to the latest version and make sure the frontend is at least v1.22.2

ComfyUI

16,738 views โ€ข 1 year ago