Memory Management for the GPU Poor, run the latest open source frontier models on consumer Nvidia GPUs
☆187Jul 20, 2026Updated last week
Alternatives and similar repositories for mmgp
Users that are interested in mmgp are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- OminiControl for the GPU Poor☆43Jan 27, 2025Updated last year
- GPU Poor Version of Hunyuan3D-2☆440Mar 29, 2025Updated last year
- Flux Fill 1.0 GO: flux Inpainting and outpainting starting with 8Gb of VRAM☆78Jan 18, 2025Updated last year
- HunyuanVideo GP: Large Video Generation Model - GPU Poor version☆464May 26, 2025Updated last year
- A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, LTX-2, Qwen Image, Hunyuan Video, LTX Video and Flux.☆6,744Updated this week
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- ☆31Jan 26, 2026Updated 6 months ago
- Cosmos1GP for the GPU Poor by DeepBeepMeep☆91Feb 15, 2025Updated last year
- Pusa: Thousands Timesteps Video Diffusion Model☆686Feb 13, 2026Updated 5 months ago
- A set of Comfyui nodes☆16Jun 21, 2026Updated last month
- YuE: Open Full-song Generation Foundation for the GPU Poor☆482Feb 14, 2025Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆17Jun 3, 2024Updated 2 years ago
- Official ConvRot implementation. A plug-and-play, convolution-like rotation module enabling efficient W4A4 quantization for diffusion mod…☆20Jul 3, 2026Updated 3 weeks ago
- Testing prompts with SDXL☆16Jul 28, 2023Updated 3 years ago
- Improving Motion in Image-to-Video Models via Adaptive Low-Pass Guidance (CVPR 2026 Highlight)☆59Feb 23, 2026Updated 5 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆33Aug 9, 2024Updated last year
- DFloat11 [NeurIPS '25]: Lossless Compression of LLMs and DiTs for Efficient GPU Inference☆652Nov 24, 2025Updated 8 months ago
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,358Jun 8, 2025Updated last year
- A simple external application for Windows that allows you to scan an existing custom_nodes directory and generate a list of the nodes ins…☆21Jul 6, 2025Updated last year
- A family of image super-resolution models with purrfect pixels.☆15Apr 29, 2026Updated 2 months ago
- ☆17Jan 1, 2024Updated 2 years ago
- SDNQ support for ComfyUI☆20Jan 6, 2026Updated 6 months ago
- 📹 A more flexible framework that can generate videos at any resolution and creates videos from images.☆2,180Updated this week
- A minimalistic, hackable code base to finetune Wan video generation model☆49Feb 22, 2026Updated 5 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- A repository of Python & PyTorch scripts which (currently) converts .safetensors models into scaled FP8 variants, utilizing gradient desc…☆26Aug 8, 2025Updated 11 months ago
- [CVPR 2026] Scaling Zero-Shot Reference-to-Video Generation☆76Apr 28, 2026Updated 3 months ago
- Bagel but with Gradio Interface☆20May 21, 2025Updated last year
- SD.Next Quantization Engine☆120Updated this week
- SkyReels-V2 with batch mode, video input (extend existing videos), and multiple prompts.☆17May 5, 2025Updated last year
- ☆19Apr 23, 2025Updated last year
- H1111 --- GUI for Video Models☆86Updated this week
- ☆427Updated this week
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,518Jan 17, 2026Updated 6 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- [AAAI 2026] Minute-Long Videos with Dual Parallelisms☆50Mar 25, 2026Updated 4 months ago
- ☆55Jun 21, 2026Updated last month
- Some Comfyui custom nodes for wan2.1 VACE, attempt to implement VACE video generation/editing in a better way.☆138Oct 31, 2025Updated 8 months ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆427Jul 5, 2025Updated last year
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆3,920Mar 7, 2026Updated 4 months ago
- [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation☆604Nov 11, 2025Updated 8 months ago
- A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for DiTs.☆1,239Updated this week