Instructions to use CaaretAI/DiT-XL-2-512 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use CaaretAI/DiT-XL-2-512 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("CaaretAI/DiT-XL-2-512", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
DiT-XL-2-512
Backup of the facebook/DiT-XL-2-512 Diffusers weights used for the Caaret image-mining run on 2026-10-26.
These are the original weights, not a re-quantized Caaret checkpoint. The noisy GEMM is applied at runtime to transformer_blocks.*.ff.net.2 (4608 → 1152), which is the width the node accepts (K >= 2048). Attention and the MLP up-projections stay in bf16 because their K is 1152 and the node rejects those certificates.
The run wrote a 512×512 ImageNet class 207 image and the node accepted block 179 (e63c6da479afe06d2cb8b6ec65c52ba2f24f8cbd8e1d6efc38623bf7b787a365).
License follows the upstream model: CC-BY-NC-4.0. Original weights: https://huggingface.co/facebook/DiT-XL-2-512
- Downloads last month
- 13
Model tree for CaaretAI/DiT-XL-2-512
Base model
facebook/DiT-XL-2-512