theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-18 22:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

kontext training

Browse Source
This commit is contained in:
Artiprocher
2025-06-30 11:00:10 +08:00
parent 44e2eecdf1
commit 157e0be49d
4 changed files with 46 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
examples/flux/model_training/full/FLUX.1-Kontext-dev.sh Normal file
View File

@@ -0,0 +1,14 @@
accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata_kontext.csv \
--data_file_keys "image,kontext_images" \
--max_pixels 1048576 \
--dataset_repeat 400 \
--model_id_with_origin_paths "black-forest-labs/FLUX.1-Kontext-dev:flux1-kontext-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
--learning_rate 1e-5 \
--num_epochs 1 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/FLUX.1-Kontext-dev_full" \
--trainable_models "dit" \
--extra_inputs "kontext_images" \
--use_gradient_checkpointing

26
examples/flux/model_training/validate_full/FLUX.1-Kontext-dev.py Normal file
View File

@@ -0,0 +1,26 @@
import torch
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
from diffsynth import load_state_dict
from PIL import Image
pipe = FluxImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="black-forest-labs/FLUX.1-Kontext-dev", origin_file_pattern="flux1-kontext-dev.safetensors"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
],
)
state_dict = load_state_dict("models/train/FLUX.1-Kontext-dev_full/epoch-0.safetensors")
pipe.dit.load_state_dict(state_dict)
image = pipe(
prompt="Make the dog turn its head around.",
kontext_images=Image.open("data/example_image_dataset/2.jpg").resize((768, 768)),
height=768, width=768,
seed=0
)
image.save("image_FLUX.1-Kontext-dev_full.jpg")