ComfyUI
The nodal workflow engine for serious diffusion.
Open Source 6–16 GB VRAM
- Min VRAM
- 6 GB
- GPU class
- Mid GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
New & trending
What's just launched, what's getting better, and what people are using right now.
Trending this week
Wan 2.2
Open-weight video diffusion from Alibaba.
Open Source 12–48 GB VRAM
- Min VRAM
- 12 GB
- GPU class
- Workstation GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Ollama
One-command local LLM runtime.
Open SourceCPU-capable
Actually FreeNo SignupOpen SourceWatermark-Free
FLUX.1 [dev]
12B parameter open-weight diffusion model.
Open Source 8–24 GB VRAM
- Min VRAM
- 8 GB
- GPU class
- High-end GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Cline
Agentic coding in VS Code — reads, writes, runs, browses.
Open Source☁ Cloud · no GPU
Actually FreeNo SignupOpen SourceWatermark-Free
HunyuanVideo
13B open-weight cinematic text-to-video.
Open Source 24–48 GB VRAM
- Min VRAM
- 24 GB
- GPU class
- Workstation GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
vLLM
High-throughput LLM serving for GPUs.
Open Source 24–80 GB VRAM
- Min VRAM
- 24 GB
- GPU class
- Datacenter GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Open WebUI
Self-hosted ChatGPT-style frontend for Ollama / OpenAI.
Open Sourcevia ollama
Actually FreeNo SignupOpen SourceWatermark-Free
Browser Use
Give your agent a real browser.
FreemiumCPU-capable
Actually FreeNo SignupOpen SourceWatermark-Free
Newly released
Wan 2.2
Open-weight video diffusion from Alibaba.
Open Source 12–48 GB VRAM
- Min VRAM
- 12 GB
- GPU class
- Workstation GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Kling 2.1
Cloud video gen with strong motion control.
Paid · from $10/mo☁ Cloud · no GPU
Watermark-FreeAPI
Magi-1
Autoregressive video diffusion at 24 GB.
Open Source 24–48 GB VRAM
- Min VRAM
- 24 GB
- GPU class
- Workstation GPU
- Quant
- FP8
Actually FreeNo SignupOpen SourceWatermark-Free
Runway Gen-4
Cinematic-quality cloud video generation.
Paid · from $15/mo☁ Cloud · no GPU
Watermark-FreeAPI
Hunyuan3D-2
Tencent's open 3D generator — multi-view, PBR, ready-to-use meshes.
Open Source 12–16 GB VRAM
- Min VRAM
- 12 GB
- GPU class
- High-end GPU
- Quant
- FP16
Actually FreeOpen SourceWatermark-FreeAPI
NVIDIA Cosmos
World-foundation models for physical AI.
Open Source 24–80 GB VRAM
- Min VRAM
- 24 GB
- GPU class
- Datacenter GPU
- Quant
- FP16
Actually FreeWatermark-FreeAPI
smolagents
Hugging Face's minimal code-writing agent library.
Open SourceCPU-capable
Actually FreeNo SignupOpen SourceWatermark-Free
MMAudio
Generate synchronized audio for any silent video.
Open Source 8–12 GB VRAM
- Min VRAM
- 8 GB
- GPU class
- Entry GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
TRELLIS
Microsoft Research's structured 3D representation model.
Open Source 16–24 GB VRAM
- Min VRAM
- 16 GB
- GPU class
- High-end GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Latest updates
Pricing changes, new features, and notable launches.
- New feature
Collapsible subgraphs land in main — huge for managing 200+ node workflows.
- model_drop
Wan 2.2 14B now runs on 24 GB cards via FP8 with the new official wrapper.
- New feature
Multimodal models now stream tokens during inference.
- New feature
Community NF4 quant now runs Flux dev on 6 GB cards in Forge.
- New feature
New block-swap option fits Flux LoRA training in 16 GB VRAM.
- model_drop
Image-to-video variant is out; ComfyUI nodes available same day.
- Trending
24 GB cards are the new local-AI floor
Searches for "24 GB VRAM" and "RTX 5090 video gen" surging this week.