FE2E INT8
Pre-quantized INT8 model for FE2E (CVPR 2026) monocular depth + surface normal estimation from a single image.
Fonte do modelo
- Tipo
- Other
- Tamanho do arquivo
- 320 MB–11,6 GB
- Modelo base
- stepfun-ai/Step1X-Edit
- Versão
- vDit int8 full
- Atualizado
- 10 de out. de 2026
- Fonte
- Hugging Face
Descrição da fonte
FE2E INT8 (Pre-quantized for CPU)
Pre-quantized INT8 model for FE2E (CVPR 2026) monocular depth + surface normal estimation from a single image.
Demo Space: WeReCooking2/FE2E-CPU
Files
| File | Size | Description |
|---|---|---|
dit_int8_full.pt | 12.4 GB | Step1X-Edit DiT (12.4B params) + LDRN LoRA merged, dynamic INT8 quantized |
vae_full.pt | 335 MB | AutoEncoder, FP32 |
Both files are saved with torch.save(model) (full model, not state_dict). Load with torch.load(..., mmap=True) to avoid doubling memory.
How it was made
- Loaded FP32 base model (
step1x-edit-i1258.safetensors) on GPU - Cast to FP32 on CPU
- Merged LDRN LoRA in full precision
- Applied
torch.quantization.quantize_dynamic(INT8 on allnn.Linearlayers) - Saved full model with
torch.save(model)
Usage
import torch
dit = torch.load("dit_int8_full.pt", map_location="cpu", weights_only=False, mmap=True)
vae = torch.load("vae_full.pt", map_location="cpu", weights_only=False, mmap=True)
Requires ~12 GB RAM with mmap loading.
Performance
| Platform | Time per image |
|---|---|
| GPU (RTX 5090, FP8 original) | ~2s |
| CPU (HF free Space, INT8) | ~29 min (768x1024) |
Single denoise step, outputs both depth and surface normal maps simultaneously.
No ONNX: PyTorch dynamo exporter produces a broken graph (100% NaN output).
Credits
- FE2E (CVPR 2026)
- Step1X-Edit base model
- rkfg/Step1X-Edit-FP8 FP8 quantization
Fontes
1 fonte
Fontes
1 fonteVerificado 10 de out.
Download files
Artefatos de modelo
2 artefatos
Artefatos de modelo
2 artefatosTrechos de fonte
2 trechos
Trechos de fonte
2 trechos--- license: mit base_model: stepfun-ai/Step1X-Edit tags: - depth-estimation - normal-estimation - quantized - int8 --- # FE2E INT8 (Pre-quantized for CPU) Pre-quantized INT8 model for [FE2E](https://github.com/AMAP-ML/FE2E) (CVPR 2026) monocular depth + surface normal estimation from a single image. **Demo Space:** [WeReCooking2/FE2E-CPU](https://huggingface.co/spaces/WeReCooking2/FE2E-CPU) ## Files | File | Size | Description | |------|------|-------------| | `dit_int8_full.pt` | 12.4 GB | Step1X-Edit DiT (12.4B params) + LDRN LoRA merged, dynamic INT8 quantized | | `vae_full.pt` | 335 MB | AutoEncoder, FP32 | Both files are saved with `torch.save(model)` (full model, not state_dict). Load with `torch.load(..., mmap=True)` to avoid doubling memory. ## How it was made 1. Loaded FP32 base model (`step1x-edit-i1258.safetensors`) on GPU 2. Cast to FP32 on CPU 3. Merged LDRN LoRA in full precision 4. Applied `torch.quantization.quantize_dynamic` (INT8 on all `nn.Linear` layers) 5. Saved full model with `torch.save(model)` ## Usage ```python import torch dit = torch.load("dit_int8_full.pt", map_location="cpu", weights_only=False, mmap=True) vae = torch.load("vae_full.pt", map_location="cpu", weights_only=False, mmap=True) ``` Requires ~12 GB RAM with mmap loading. ## Performance | Platform | Time per image | |----------|---------------| | GPU (RTX 5090, FP8 original) | ~2s | | CPU (HF free Space, INT8) | ~29 min (768x1024) | Single denoise step, outputs both depth and surface normal maps simultaneously. > No ONNX: PyTorch dynamo exporter produces a broken graph (100% NaN output). ## Credits - [FE2E](https://github.com/AMAP-ML/FE2E) (CVPR 2026) - [Step1X-Edit](https://github.com/stepfun-ai/Step1X-Edit) base model - [rkfg/Step1X-Edit-FP8](https://huggingface.co/rkfg/Step1X-Edit-FP8) FP8 quantization
Source context: 0 downloads · 0 likes · Pipeline depth-estimation · Repo WeReCooking2/FE2E-INT8
