kontext

examples/flux/model_inference/FLUX.1-Kontext-dev.py

@@ -0,0 +1,54 @@
+import torch
+from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
+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"),
+    ],
+)
+
+image_1 = pipe(
+    prompt="a beautiful Asian long-haired female college student.",
+    embedded_guidance=2.5,
+    seed=1,
+)
+image_1.save("image_1.jpg")
+
+image_2 = pipe(
+    prompt="transform the style to anime style.",
+    kontext_images=image_1,
+    embedded_guidance=2.5,
+    seed=2,
+)
+image_2.save("image_2.jpg")
+
+image_3 = pipe(
+    prompt="let her smile.",
+    kontext_images=image_1,
+    embedded_guidance=2.5,
+    seed=3,
+)
+image_3.save("image_3.jpg")
+
+image_4 = pipe(
+    prompt="let the girl play basketball.",
+    kontext_images=image_1,
+    embedded_guidance=2.5,
+    seed=4,
+)
+image_4.save("image_4.jpg")
+
+image_5 = pipe(
+    prompt="move the girl to a park, let her sit on a chair.",
+    kontext_images=image_1,
+    embedded_guidance=2.5,
+    seed=5,
+)
+image_5.save("image_5.jpg")

examples/flux/model_training/lora/FLUX.1-Kontext-dev.sh

@@ -0,0 +1,17 @@
+accelerate launch 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-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLUX.1-Kontext-dev_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "a_to_qkv,b_to_qkv,ff_a.0,ff_a.2,ff_b.0,ff_b.2,a_to_out,b_to_out,proj_out,norm.linear,norm1_a.linear,norm1_b.linear,to_qkv_mlp" \
+  --lora_rank 32 \
+  --align_to_opensource_format \
+  --extra_inputs "kontext_images" \
+  --use_gradient_checkpointing

examples/flux/model_training/validate_lora/FLUX.1-Kontext-dev.py

@@ -0,0 +1,24 @@
+import torch
+from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
+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"),
+    ],
+)
+pipe.load_lora(pipe.dit, "models/train/FLUX.1-Kontext-dev_lora/epoch-4.safetensors", alpha=1)
+
+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_lora.jpg")