Instructions to use Jinl/DiffusionNFT-baselines with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Jinl/DiffusionNFT-baselines with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-3.5-medium", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Jinl/DiffusionNFT-baselines") 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 experiment_provenance.csv from Jinl/DiffusionNFT-baselines: direct link, hf CLI and curl.
- Browser
- Download file 2 kB
-
https://huggingface.co/Jinl/DiffusionNFT-baselines/resolve/main/experiment_provenance.csv
- Command line
-
hf download hf://Jinl/DiffusionNFT-baselines/experiment_provenance.csv
-
curl -L -o experiment_provenance.csv https://huggingface.co/Jinl/DiffusionNFT-baselines/resolve/main/experiment_provenance.csv
2 kB
| run_name,classification,code_provenance,algorithm,git_commit,git_remote,launch_args,rank_aware_enabled,pl_version,weight_mode,mix_lambda,aux_mu,eval_num_steps,train_batch_size,num_batches_per_epoch,gradient_accumulation_steps,recorded_save_dir,last_logged_step,metadata_path,config_path,notes | |
| nft_sd3_geneval_2026.04.20_11.18.57,原版NFT baseline候选,原仓库commit;未保存工作区快照,NFT baseline,cbb14f84b8312b620390dfcbe2fab69c1383b104,https://github.com/NVlabs/DiffusionNFT.git,--config config/nft.py:sd3_geneval,absent,,,,,40,9,16,16,logs/nft/sd3/geneval,251,logs/nft_sd3_geneval_2026.04.20_11.18.57/wandb/run-20260420_111901-run_20260420_5eee4cae/files/wandb-metadata.json,logs/nft_sd3_geneval_2026.04.20_11.18.57/wandb/run-20260420_111901-run_20260420_5eee4cae/files/config.yaml,remote=NVlabs/DiffusionNFT,commit=cbb14f8,主要训练/采样配置与上游一致;无代码快照或工作区diff,不能证明逐文件未改。 三次早期运行共用save_dir;现存该目录checkpoint时间对应4/23运行,不能把同路径文件归给4/20或4/22。 logs/nft/sd3_v0/geneval/checkpoints(0至240)时间与本次运行吻合,疑为归档;未发现直接迁移记录。 | |
| nft_sd3_geneval_2026.04.22_04.13.06,原版NFT baseline候选,原仓库commit;未保存工作区快照,NFT baseline,cbb14f84b8312b620390dfcbe2fab69c1383b104,https://github.com/NVlabs/DiffusionNFT.git,--config config/nft.py:sd3_geneval,absent,,,,,40,9,16,16,logs/nft/sd3/geneval,39,logs/nft_sd3_geneval_2026.04.22_04.13.06/wandb/run-20260422_041321-run_20260422_e483d067/files/wandb-metadata.json,logs/nft_sd3_geneval_2026.04.22_04.13.06/wandb/run-20260422_041321-run_20260422_e483d067/files/config.yaml,remote=NVlabs/DiffusionNFT,commit=cbb14f8,主要训练/采样配置与上游一致;无代码快照或工作区diff,不能证明逐文件未改。 三次早期运行共用save_dir;现存该目录checkpoint时间对应4/23运行,不能把同路径文件归给4/20或4/22。 | |