Instructions to use kimi000/Flux1-Dev-4Step-2000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kimi000/Flux1-Dev-4Step-2000 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("kimi000/Flux1-Dev-4Step-2000", 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
Download validation_report.json from kimi000/Flux1-Dev-4Step-2000: direct link, hf CLI and curl.
- Browser
- Download file 504 Bytes
-
https://huggingface.co/kimi000/Flux1-Dev-4Step-2000/resolve/main/validation_report.json
- Command line
-
hf download hf://kimi000/Flux1-Dev-4Step-2000/validation_report.json
-
curl -L -o validation_report.json https://huggingface.co/kimi000/Flux1-Dev-4Step-2000/resolve/main/validation_report.json
504 Bytes
| { | |
| "status": "passed", | |
| "gpu_name": "NVIDIA H100 80GB HBM3", | |
| "standalone_diffusers_load": true, | |
| "all_merged_tensor_hashes_match": 1160, | |
| "native_sampler_latent_max_abs": 0.0, | |
| "native_text_encoder_parity": true, | |
| "scheduler_parity": true, | |
| "transformer_calls": 4, | |
| "cpu_offload": "passed", | |
| "height": 1024, | |
| "width": 1024, | |
| "vae_dtype": "torch.float32", | |
| "guidance_embedding": 3.5, | |
| "external_cfg": 1.0, | |
| "inference_seconds": 12.483246803283691, | |
| "elapsed_seconds": 74.13123774528503 | |
| } | |