Text-to-Image
Diffusers
Safetensors
Diffusion Single File
English
FluxControlPipeline
image-generation
flux
Instructions to use srcphag/Flux1-Depth-Dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use srcphag/Flux1-Depth-Dev with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("srcphag/Flux1-Depth-Dev", torch_dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Diffusion Single File
How to use srcphag/Flux1-Depth-Dev with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
| from safetensors import safe_open | |
| with safe_open("flux1-depth-dev_fp4_merged_model.safetensors", framework="pt") as f: | |
| keys = f.keys() | |
| has_vae = any('vae' in k or 'decoder' in k for k in keys) | |
| has_clip = any('text_encoder' in k or 'clip' in k for k in keys) | |
| has_unet = any('unet' in k or 'transformer' in k for k in keys) | |
| print(f"VAE: {has_vae}, CLIP: {has_clip}, UNet: {has_unet}") |