Instructions to use zjwfufu/SMD-FLUX.1-dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use zjwfufu/SMD-FLUX.1-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("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("zjwfufu/SMD-FLUX.1-dev") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Download sampling.json from zjwfufu/SMD-FLUX.1-dev: direct link, hf CLI and curl.
- Browser
- Download file 773 Bytes
-
https://huggingface.co/zjwfufu/SMD-FLUX.1-dev/resolve/main/sampling.json
- Command line
-
hf download hf://zjwfufu/SMD-FLUX.1-dev/sampling.json
-
curl -L -o sampling.json https://huggingface.co/zjwfufu/SMD-FLUX.1-dev/resolve/main/sampling.json
773 Bytes
| { | |
| "schema_version": "1.0", | |
| "network_family": "flux", | |
| "model_id": "black-forest-labs/FLUX.1-dev", | |
| "precision": "bfloat16", | |
| "weights": "lora/lora.safetensors", | |
| "sampler": { | |
| "type": "flow_match_euler_student", | |
| "student_sample_steps": 4, | |
| "final_step_size_scale": 0.5, | |
| "embedded_guidance_scale": 3.5, | |
| "input_shape": [ | |
| 16, | |
| 96, | |
| 170 | |
| ] | |
| }, | |
| "noise_scheduler": { | |
| "type": "flow_match_euler", | |
| "shift": 3.1496510428919113, | |
| "base_shift": 0.5, | |
| "max_shift": 1.15, | |
| "base_seq_len": 256, | |
| "max_seq_len": 4096, | |
| "time_shift_type": "exponential", | |
| "dynamic_shift": true, | |
| "empirical_steps": 0, | |
| "max_t": 0.999, | |
| "min_t": 0.0 | |
| }, | |
| "base_model_revision": "3de623fc3c33e44ffbe2bad470d0f45bccf2eb21" | |
| } | |