We are excited to introduce Wan2.2, a major upgrade to our foundational video models. With Wan2.2, we have focused on incorporating the following innovations: This repository also includes our I2V-A14B model, designed for image-to-video generation, supporting both 480P and 720P resolutions. Built with a Mixture-of-Experts (MoE) architecture, it achieves more stable video synthesis with reduced unrealistic camera movements and offers enhanced support for diverse stylized scenes. Your browser does not support the video tag. If your research or project builds upon Wan2.1 or Wan2.2, we welcome you to share it with us so we can highlight it for the broader community. - Wan2.2 Text-to-Video - [x]…
Open-weight model · Image to video
WorldCrafter-Base
by ARC Lab, Tencent TencentARC/WorldCrafter-Base
WorldCrafter-Base is an open-weight model for image to video from ARC Lab, Tencent. It has 14.3B parameters. At 16-bit it needs about 34.3 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Base transformer weights and their matching camera adapter and LoRA for the WorldCrafter inference code. Place this directory beside WorldCrafter-Fast.
Parameters14.3B
Context—
Weights59.5 GB
License—
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve WorldCrafter-Base (14.3B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 28.6 GB | 34.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 14.3 GB | 17.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 7.1 GB | 8.6 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 18, 2026.
WorldCrafter-Base on every accelerator the SAVRN Index prices, at every precision
Model Card
Base transformer weights and their matching camera adapter and LoRA for the WorldCrafter inference code. Place this directory beside WorldCrafter-Fast. Base reads the following shared folders from Fast: repencoder/, textencoder/, tokenizer/, vae/, and scheduler/. Base does not need Fast's transformer or adapter folders. The relative path is configured in inferenceconfig.json. Keep the Base-specific transformer/ and adapter/ together. SHA256SUMS covers the packaged Base files; shared component hashes are recorded in Fast's package.
Excerpt from the card by ARC Lab, Tencent.
Identity and Version
- Repository
- TencentARC/WorldCrafter-Base
- Publisher
- ARC Lab, Tencent
- Task
- Image to video
- Modality
- Other
- Library
- diffusers
- Parameters
- 14.3B parameters
- Languages
- Not stated by the source
- Revision
- d6b4731d4cec53f90b6afaee5a0f1b77d29979aa
- First published
- 2026-09-21
- Last updated
- 2026-09-22
Files and Weights
16 files, 59.5 GB in total. The weights are 8 files totalling 59.5 GB in pth, safetensors.
Weights8 files · 59.5 GB
Configuration5 files · 99.1 KB
Documentation1 file · 1.1 KB
Other1 file · 1.5 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapter/camera_adapter.pth | Weights | 1.1 GB | 7e1d355cf8d4 |
| adapter/pytorch_lora_weights.safetensors | Weights | 1.2 GB | 99426db2777b |
| transformer/diffusion_pytorch_model-00001-of-00006.safetensors | Weights | 10.0 GB | 6cac837bbcf5 |
| transformer/diffusion_pytorch_model-00002-of-00006.safetensors | Weights | 9.9 GB | bf005847bfa3 |
| transformer/diffusion_pytorch_model-00003-of-00006.safetensors | Weights | 9.9 GB | 6c5d4ae0816a |
| transformer/diffusion_pytorch_model-00004-of-00006.safetensors | Weights | 9.8 GB | 28fd1c7dda85 |
| transformer/diffusion_pytorch_model-00005-of-00006.safetensors | Weights | 9.8 GB | 099a07a55063 |
| transformer/diffusion_pytorch_model-00006-of-00006.safetensors | Weights | 7.6 GB | 36f2c49db52c |
| adapter/config.json | Configuration | 186 B | — |
| inference_config.json | Configuration | 86 B | — |
| model_index.json | Configuration | 417 B | — |
| transformer/config.json | Configuration | 665 B | — |
| transformer/diffusion_pytorch_model.safetensors.index.json | Configuration | 97.8 KB | — |
| README.md | Documentation | 1.1 KB | — |
| SHA256SUMS | Other | 1.5 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 59.5 GB
Download from ARC Lab, Tencent
Released by ARC Lab, Tencent through its official repository on Hugging Face.
Built From
- Described by arXiv:2609.24984
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 59.5 GB |
| 16-bit | 28.6 GB |
| 8-bit | 14.3 GB |
| 4-bit | 7.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About WorldCrafter-Base
How much GPU memory does WorldCrafter-Base need?
About 34.3 GB at 16-bit and 8.6 GB at 4-bit: the weights (14.3B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run WorldCrafter-Base on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Similar Models
This model card focuses on the LTX-2 model, as presented in the paper LTX-2: Efficient Joint Audio-Visual Foundation Model. The codebase is available here. LTX-2 is a DiT-based audio-video foundation model designed to generate synchronized video and audio within a single model. It brings together the core building blocks of modern video generation, with open weights and a focus on practical, local execution. LTX-2 is accessible right away via the following links: You can use the models - full, distilled, upscalers and any derivatives of the models - for purposes under the license. We recommend you use the built-in LTXVideo nodes that can be found in the ComfyUI Manager. For manual…
This model card focuses on the model associated with the LTX-Video model, codebase available here. LTX-Video is the first DiT-based video generation model capable of generating high-quality videos in real-time. It produces 30 FPS videos at a 1216×704 resolution faster than they can be watched. Trained on a large-scale dataset of diverse videos, the model generates high-resolution videos with realistic and varied content. You can use the model for purposes under the license: - 2B version 0.9: license - 2B version 0.9.1 license - 2B version 0.9.5 license - 2B version 0.9.6-dev license - 2B version 0.9.6-distilled license - 13B version 0.9.7-dev license - 13B version 0.9.7-dev-fp8 license…
Repackaged model files for ComfyUI. - https://huggingface.co/nvidia/ChronoEdit-14B-Diffusers - https://huggingface.co/Wan-AI/Wan2.2-Animate-14B - https://huggingface.co/alibaba-pai/Wan2.2-Fun-A14B-Control-Camera - https://huggingface.co/alibaba-pai/Wan2.2-Fun-A14B-Control - https://huggingface.co/alibaba-pai/Wan2.2-Fun-5B-Control - https://huggingface.co/alibaba-pai/Wan2.2-Fun-5B-InP - https://huggingface.co/alibaba-pai/Wan2.2-Fun-A14B-InP - https://huggingface.co/alibaba-pai/Wan2.2-VACE-Fun-A14B - https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B - https://huggingface.co/Wan-AI/Wan2.2-S2V-14B - https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B - https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B…
LTX-2.5 is an open world model with open weights, built for local execution and fine-tuning. Its established use is generating synchronized, high-fidelity video and audio from text, image, and video inputs; applicability to emerging domains such as robotics and physical AI is developing. Full control and customization — self-host on your own infrastructure. No per-generation billing, no per-seat lock-in, no forced API dependency. Revenue is measured across the whole entity, including subsidiaries and affiliates under common control. The full, binding terms live in LICENSE. - Native multishot generation — generate connected scenes in a single pass: multiple shots that hold character…
LTX-2.5 is an open world model with open weights, built for local execution and fine-tuning. Its established use is generating synchronized, high-fidelity video and audio from text, image, and video inputs; applicability to emerging domains such as robotics and physical AI is developing. Full control and customization — self-host on your own infrastructure. No per-generation billing, no per-seat lock-in, no forced API dependency. Revenue is measured across the whole entity, including subsidiaries and affiliates under common control. The full, binding terms live in LICENSE. - Native multishot generation — generate connected scenes in a single pass: multiple shots that hold character…