Tencent/HunyuanCustom
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
Language:Python
Total stars: 157
Stars trend:
#python
#audiodriven, #diffusionmodels, #imagetovideo, #imagetovideogeneration, #videoediting, #videogeneration
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
Language:Python
Total stars: 157
Stars trend:
9 May 2025
1am █▋ +13
2am ███▏ +25
3am ██████▊ +54
4am ██▌ +20
5am ███▍ +27#python
#audiodriven, #diffusionmodels, #imagetovideo, #imagetovideogeneration, #videoediting, #videogeneration
Lightricks/ComfyUI-LTXVideo
LTX-Video Support for ComfyUI
Language:Python
Total stars: 1534
Stars trend:
#python
#comfyui, #diffusionmodels, #dit, #imagetovideo, #imagetovideogeneration, #texttoimage, #texttoimagegeneration
LTX-Video Support for ComfyUI
Language:Python
Total stars: 1534
Stars trend:
11 May 2025
3pm █ +8
4pm ▏ +1
5pm ▊ +6
6pm ▌ +4
7pm ▌ +4
8pm ▋ +5
9pm ▍ +3
10pm ▍ +3
11pm ▉ +7
12 May 2025
12am █ +8
1am █▉ +15
2am █▋ +13#python
#comfyui, #diffusionmodels, #dit, #imagetovideo, #imagetovideogeneration, #texttoimage, #texttoimagegeneration
Gen-Verse/MMaDA
MMaDA - Open-Sourced Multimodal Large Diffusion Language Models
Language:Python
Total stars: 181
Stars trend:
#python
#diffusionmodels, #llmreasoning, #unifiedmultimodalunderstandingandgeneration
MMaDA - Open-Sourced Multimodal Large Diffusion Language Models
Language:Python
Total stars: 181
Stars trend:
22 May 2025
1am ▍ +3
2am █▏ +9
3am ██▍ +19
4am ██▍ +19
5am █▊ +14
6am ██ +16
7am ███▋ +29
8am ██▋ +21#python
#diffusionmodels, #llmreasoning, #unifiedmultimodalunderstandingandgeneration
EzioBy/Ditto
[Preprint 2025] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset
Language:Python
Total stars: 262
Stars trend:
#python
#diffusionmodels, #syntheticdata, #videoediting
[Preprint 2025] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset
Language:Python
Total stars: 262
Stars trend:
22 Oct 2025
11pm ▏ +1
23 Oct 2025
12am +0
1am ▏ +1
2am ▏ +1
3am ▌ +4
4am ▍ +3
5am ▊ +6
6am ▏ +1
7am ▍ +3
8am ▏ +1
9am ▉ +7
10am ▍ +3#python
#diffusionmodels, #syntheticdata, #videoediting
caiyuanhao1998/Open-DiffusionGS
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction (ICCV 2025)
Language:Python
Total stars: 522
Stars trend:
#python
#3ddiffusionmodels, #3dgaussiansplatting, #3dgeneration, #3dgraphics, #3dmeshgeneration, #3dmeshing, #3dscenegeneration, #3dvision, #3dgs, #diffusionmodels, #imageto3d, #textto3d
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction (ICCV 2025)
Language:Python
Total stars: 522
Stars trend:
27 Oct 2025
2am ██▊ +22
3am ▏ +1
4am +0
5am +0
6am +0
7am +0
8am +0
9am +0
10am +0
11am ▎ +2
12pm ▎ +2#python
#3ddiffusionmodels, #3dgaussiansplatting, #3dgeneration, #3dgraphics, #3dmeshgeneration, #3dmeshing, #3dscenegeneration, #3dvision, #3dgs, #diffusionmodels, #imageto3d, #textto3d
Visionary-Laboratory/visionary
Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform
Language:Python
Total stars: 94
Stars trend:
#python
#3dgs, #4dgs, #avatar, #computergraphics, #computervision, #diffusionmodels, #gaussiansplatting, #neuralrendering, #onnx, #threejs, #viewer, #webgpu, #worldmodel
Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform
Language:Python
Total stars: 94
Stars trend:
10 Dec 2025
2am ▏ +1
3am ▏ +1
4am ▊ +6
5am ██▊ +22
6am █ +8
7am ▌ +4#python
#3dgs, #4dgs, #avatar, #computergraphics, #computervision, #diffusionmodels, #gaussiansplatting, #neuralrendering, #onnx, #threejs, #viewer, #webgpu, #worldmodel
thu-ml/TurboDiffusion
TurboDiffusion: 100–205× Acceleration of Video Diffusion Models
Language:Python
Total stars: 431
Stars trend:
#python
#aiinfra, #diffusionmodels, #inferenceacceleration, #mlsystem, #rcm, #sageattention, #sparselinearattention, #videogeneration
TurboDiffusion: 100–205× Acceleration of Video Diffusion Models
Language:Python
Total stars: 431
Stars trend:
17 Dec 2025
1am ▉ +7
2am ▋ +5
3am ▋ +5
4am ▋ +5
5am ▍ +3
6am ▉ +7
7am ▏ +1
8am █ +8
9am ▏ +1
10am +0
11am ▊ +6
12pm ▌ +4#python
#aiinfra, #diffusionmodels, #inferenceacceleration, #mlsystem, #rcm, #sageattention, #sparselinearattention, #videogeneration
NVlabs/FastGen
NVIDIA FastGen: Fast Generation from Diffusion Models
Language:Python
Total stars: 118
Stars trend:
#python
#diffusionmodels, #distillation
NVIDIA FastGen: Fast Generation from Diffusion Models
Language:Python
Total stars: 118
Stars trend:
27 Jan 2026
6pm ▏ +1
7pm +0
8pm +0
9pm +0
10pm ▎ +2
11pm ▌ +4
28 Jan 2026
12am ▍ +3
1am ▉ +7
2am ▋ +5
3am █▏ +9
4am ▍ +3
5am █ +8#python
#diffusionmodels, #distillation
MaximeVandegar/Papers-in-100-Lines-of-Code
Implementation of papers in 100 lines of code.
Language:Python
Total stars: 2246
Stars trend:
#python
#3d, #aes, #artificialintelligence, #deeplearning, #diffusionmodels, #educational, #gans, #generativemodel, #implementationofresearchpaper, #inverserendering, #machinelearning, #metalearning, #nerf, #neuralradiancefields, #papers, #python, #pytorch, #reinforcementlearning, #research, #rl
Implementation of papers in 100 lines of code.
Language:Python
Total stars: 2246
Stars trend:
28 Jan 2026
1am ▊ +6
2am ▉ +7
3am █ +8
4am ▋ +5
5am ▌ +4
6am ▋ +5
7am ▌ +4
8am ▏ +1
9am ▏ +1
10am +0
11am +0
12pm ▎ +2#python
#3d, #aes, #artificialintelligence, #deeplearning, #diffusionmodels, #educational, #gans, #generativemodel, #implementationofresearchpaper, #inverserendering, #machinelearning, #metalearning, #nerf, #neuralradiancefields, #papers, #python, #pytorch, #reinforcementlearning, #research, #rl
wiltodelta/remove-ai-watermarks
CLI and library for removing visible (Gemini) and invisible (SynthID, C2PA, EXIF) AI watermarks from images
Language:Python
Total stars: 2007
Stars trend:
#python
#ai, #c2pa, #cli, #computervision, #diffusionmodels, #gemini, #imageprocessing, #metadata, #python, #synthid, #watermarkremoval
CLI and library for removing visible (Gemini) and invisible (SynthID, C2PA, EXIF) AI watermarks from images
Language:Python
Total stars: 2007
Stars trend:
23 May 2026
5am ▍ +3
6am ▎ +2
7am ▋ +5
8am ▎ +2
9am ▉ +7
10am +0
11am ▎ +2
12pm ▎ +2
1pm ▏ +1
2pm ▏ +1#python
#ai, #c2pa, #cli, #computervision, #diffusionmodels, #gemini, #imageprocessing, #metadata, #python, #synthid, #watermarkremoval