Skip to content

Add missing dataset download to Qwen-Image validate examples #1667

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
rakhimovv wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add missing dataset download to Qwen-Image validate examples #1667

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions examples/qwen_image/model_training/validate_full/FireRed-Image-Edit-1.0.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
from PIL import Image
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from diffsynth import load_state_dict
from modelscope import dataset_snapshot_download

pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
Expand All @@ -17,6 +18,12 @@
state_dict = load_state_dict("models/train/FireRed-Image-Edit-1.0_full/epoch-1.safetensors")
pipe.dit.load_state_dict(state_dict)

dataset_snapshot_download(
dataset_id="DiffSynth-Studio/example_image_dataset",
local_dir="./data/example_image_dataset",
allow_file_pattern="edit/*.jpg"
)

prompt = "Change the color of the dress in Figure 1 to the color shown in Figure 2."
images = [
Image.open("data/example_image_dataset/edit/image1.jpg").resize((1024, 1024)),
Expand Down
7 changes: 7 additions & 0 deletions examples/qwen_image/model_training/validate_full/FireRed-Image-Edit-1.1.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
from PIL import Image
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from diffsynth import load_state_dict
from modelscope import dataset_snapshot_download

pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
Expand All @@ -17,6 +18,12 @@
state_dict = load_state_dict("models/train/FireRed-Image-Edit-1.1_full/epoch-1.safetensors")
pipe.dit.load_state_dict(state_dict)

dataset_snapshot_download(
dataset_id="DiffSynth-Studio/example_image_dataset",
local_dir="./data/example_image_dataset",
allow_file_pattern="edit/*.jpg"
)

prompt = "Change the color of the dress in Figure 1 to the color shown in Figure 2."
images = [
Image.open("data/example_image_dataset/edit/image1.jpg").resize((1024, 1024)),
Expand Down
7 changes: 7 additions & 0 deletions examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2509.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
from PIL import Image
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from diffsynth import load_state_dict
from modelscope import dataset_snapshot_download

pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
Expand All @@ -17,6 +18,12 @@
state_dict = load_state_dict("models/train/Qwen-Image-Edit-2509_full/epoch-1.safetensors")
pipe.dit.load_state_dict(state_dict)

dataset_snapshot_download(
dataset_id="DiffSynth-Studio/example_image_dataset",
local_dir="./data/example_image_dataset",
allow_file_pattern="edit/*.jpg"
)

prompt = "Change the color of the dress in Figure 1 to the color shown in Figure 2."
images = [
Image.open("data/example_image_dataset/edit/image1.jpg").resize((1024, 1024)),
Expand Down
7 changes: 7 additions & 0 deletions examples/qwen_image/model_training/validate_full/Qwen-Image-Edit-2511.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
from PIL import Image
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from diffsynth import load_state_dict
from modelscope import dataset_snapshot_download

pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
Expand All @@ -17,6 +18,12 @@
state_dict = load_state_dict("models/train/Qwen-Image-Edit-2511_full/epoch-1.safetensors")
pipe.dit.load_state_dict(state_dict)

dataset_snapshot_download(
dataset_id="DiffSynth-Studio/example_image_dataset",
local_dir="./data/example_image_dataset",
allow_file_pattern="edit/*.jpg"
)

prompt = "Change the color of the dress in Figure 1 to the color shown in Figure 2."
images = [
Image.open("data/example_image_dataset/edit/image1.jpg").resize((1024, 1024)),
Expand Down
7 changes: 7 additions & 0 deletions examples/qwen_image/model_training/validate_full/Qwen-Image-Edit.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
from PIL import Image
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from diffsynth import load_state_dict
from modelscope import dataset_snapshot_download

pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
Expand All @@ -17,6 +18,12 @@
state_dict = load_state_dict("models/train/Qwen-Image-Edit_full/epoch-1.safetensors")
pipe.dit.load_state_dict(state_dict)

dataset_snapshot_download(
dataset_id="DiffSynth-Studio/example_image_dataset",
local_dir="./data/example_image_dataset",
allow_file_pattern="edit/image1.jpg"
)

prompt = "将裙子改为粉色"
image = Image.open("data/example_image_dataset/edit/image1.jpg").resize((1024, 1024))
image = pipe(prompt, edit_image=image, seed=0, num_inference_steps=40, height=1024, width=1024)
Expand Down
7 changes: 7 additions & 0 deletions examples/qwen_image/model_training/validate_full/Qwen-Image-Layered-Control.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
from diffsynth import load_state_dict
from PIL import Image
import torch
from modelscope import dataset_snapshot_download


pipe = QwenImagePipeline.from_pretrained(
Expand All @@ -16,6 +17,12 @@
)
state_dict = load_state_dict("models/train/Qwen-Image-Layered-Control_full/epoch-1.safetensors")
pipe.dit.load_state_dict(state_dict)

dataset_snapshot_download(
dataset_id="DiffSynth-Studio/example_image_dataset",
local_dir="./data/example_image_dataset",
allow_file_pattern="layer/image.png"
)
prompt = "Text 'HELLO' and 'Have a great day'"
input_image = Image.open("data/example_image_dataset/layer/image.png").convert("RGBA").resize((864, 480))
images = pipe(
Expand Down
7 changes: 7 additions & 0 deletions examples/qwen_image/model_training/validate_full/Qwen-Image-Layered.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
from diffsynth import load_state_dict
from PIL import Image
import torch
from modelscope import dataset_snapshot_download


pipe = QwenImagePipeline.from_pretrained(
Expand All @@ -16,6 +17,12 @@
)
state_dict = load_state_dict("models/train/Qwen-Image-Layered_full/epoch-1.safetensors")
pipe.dit.load_state_dict(state_dict)

dataset_snapshot_download(
dataset_id="DiffSynth-Studio/example_image_dataset",
local_dir="./data/example_image_dataset",
allow_file_pattern="layer/image.png"
)
prompt = "a poster"
input_image = Image.open("data/example_image_dataset/layer/image.png").convert("RGBA").resize((864, 480))
images = pipe(
Expand Down
7 changes: 7 additions & 0 deletions examples/qwen_image/model_training/validate_lora/FireRed-Image-Edit-1.0.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
import torch
from PIL import Image
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from modelscope import dataset_snapshot_download

pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
Expand All @@ -15,6 +16,12 @@
)
pipe.load_lora(pipe.dit, "models/train/FireRed-Image-Edit-1.0_lora/epoch-4.safetensors")

dataset_snapshot_download(
dataset_id="DiffSynth-Studio/example_image_dataset",
local_dir="./data/example_image_dataset",
allow_file_pattern="edit/*.jpg"
)

prompt = "Change the color of the dress in Figure 1 to the color shown in Figure 2."
images = [
Image.open("data/example_image_dataset/edit/image1.jpg").resize((1024, 1024)),
Expand Down
7 changes: 7 additions & 0 deletions examples/qwen_image/model_training/validate_lora/FireRed-Image-Edit-1.1.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
import torch
from PIL import Image
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from modelscope import dataset_snapshot_download

pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
Expand All @@ -15,6 +16,12 @@
)
pipe.load_lora(pipe.dit, "models/train/FireRed-Image-Edit-1.1_lora/epoch-4.safetensors")

dataset_snapshot_download(
dataset_id="DiffSynth-Studio/example_image_dataset",
local_dir="./data/example_image_dataset",
allow_file_pattern="edit/*.jpg"
)

prompt = "Change the color of the dress in Figure 1 to the color shown in Figure 2."
images = [
Image.open("data/example_image_dataset/edit/image1.jpg").resize((1024, 1024)),
Expand Down
7 changes: 7 additions & 0 deletions examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2509.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
import torch
from PIL import Image
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from modelscope import dataset_snapshot_download

pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
Expand All @@ -15,6 +16,12 @@
)
pipe.load_lora(pipe.dit, "models/train/Qwen-Image-Edit-2509_lora/epoch-4.safetensors")

dataset_snapshot_download(
dataset_id="DiffSynth-Studio/example_image_dataset",
local_dir="./data/example_image_dataset",
allow_file_pattern="edit/*.jpg"
)

prompt = "Change the color of the dress in Figure 1 to the color shown in Figure 2."
images = [
Image.open("data/example_image_dataset/edit/image1.jpg").resize((1024, 1024)),
Expand Down
7 changes: 7 additions & 0 deletions examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit-2511.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
import torch
from PIL import Image
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from modelscope import dataset_snapshot_download

pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
Expand All @@ -15,6 +16,12 @@
)
pipe.load_lora(pipe.dit, "models/train/Qwen-Image-Edit-2511_lora/epoch-4.safetensors")

dataset_snapshot_download(
dataset_id="DiffSynth-Studio/example_image_dataset",
local_dir="./data/example_image_dataset",
allow_file_pattern="edit/*.jpg"
)

prompt = "Change the color of the dress in Figure 1 to the color shown in Figure 2."
images = [
Image.open("data/example_image_dataset/edit/image1.jpg").resize((1024, 1024)),
Expand Down
7 changes: 7 additions & 0 deletions examples/qwen_image/model_training/validate_lora/Qwen-Image-Edit.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
import torch
from PIL import Image
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from modelscope import dataset_snapshot_download

pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
Expand All @@ -15,6 +16,12 @@
)
pipe.load_lora(pipe.dit, "models/train/Qwen-Image-Edit_lora/epoch-4.safetensors")

dataset_snapshot_download(
dataset_id="DiffSynth-Studio/example_image_dataset",
local_dir="./data/example_image_dataset",
allow_file_pattern="edit/image1.jpg"
)

prompt = "将裙子改为粉色"
image = Image.open("data/example_image_dataset/edit/image1.jpg").resize((1024, 1024))
image = pipe(prompt, edit_image=image, seed=0, num_inference_steps=40, height=1024, width=1024)
Expand Down
7 changes: 7 additions & 0 deletions examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen-Poster.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
import torch
from PIL import Image
from modelscope import dataset_snapshot_download


pipe = QwenImagePipeline.from_pretrained(
Expand All @@ -15,6 +16,12 @@
)
pipe.load_lora(pipe.dit, "models/train/Qwen-Image-EliGen-Poster_lora/epoch-4.safetensors")

dataset_snapshot_download(
dataset_id="DiffSynth-Studio/example_image_dataset",
local_dir="./data/example_image_dataset",
allow_file_pattern="eligen/*.png"
)


entity_prompts = ["A beautiful girl", "sign 'Entity Control'", "shorts", "shirt"]
global_prompt = "A beautiful girl wearing shirt and shorts in the street, holding a sign 'Entity Control'"
Expand Down
7 changes: 7 additions & 0 deletions examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
import torch
from PIL import Image
from modelscope import dataset_snapshot_download


pipe = QwenImagePipeline.from_pretrained(
Expand All @@ -15,6 +16,12 @@
)
pipe.load_lora(pipe.dit, "models/train/Qwen-Image-EliGen_lora/epoch-4.safetensors")

dataset_snapshot_download(
dataset_id="DiffSynth-Studio/example_image_dataset",
local_dir="./data/example_image_dataset",
allow_file_pattern="eligen/*.png"
)


entity_prompts = ["A beautiful girl", "sign 'Entity Control'", "shorts", "shirt"]
global_prompt = "A beautiful girl wearing shirt and shorts in the street, holding a sign 'Entity Control'"
Expand Down
7 changes: 7 additions & 0 deletions examples/qwen_image/model_training/validate_lora/Qwen-Image-In-Context-Control-Union.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
from PIL import Image
import torch
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from modelscope import dataset_snapshot_download

pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
Expand All @@ -13,6 +14,12 @@
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)
pipe.load_lora(pipe.dit, "models/train/Qwen-Image-In-Context-Control-Union_lora/epoch-4.safetensors")

dataset_snapshot_download(
dataset_id="DiffSynth-Studio/example_image_dataset",
local_dir="./data/example_image_dataset",
allow_file_pattern="canny/image_1.jpg"
)
image = Image.open("data/example_image_dataset/canny/image_1.jpg").resize((1024, 1024))
prompt = "Context_Control. a dog"
image = pipe(prompt=prompt, seed=0, context_image=image, height=1024, width=1024)
Expand Down
6 changes: 6 additions & 0 deletions examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control-V2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,12 @@
)
pipe.load_lora(pipe.dit, "models/train/Qwen-Image-Layered-Control-V2_lora/epoch-4.safetensors")

dataset_snapshot_download(
dataset_id="DiffSynth-Studio/example_image_dataset",
local_dir="./data/example_image_dataset",
allow_file_pattern="layer_v2/*.png"
)

prompt = "Text 'APRIL'"
input_image = Image.open("data/example_image_dataset/layer_v2/image_1.png").convert("RGBA").resize((1024, 1024))
image = pipe(
Expand Down
7 changes: 7 additions & 0 deletions examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
from diffsynth import load_state_dict
from PIL import Image
import torch
from modelscope import dataset_snapshot_download


pipe = QwenImagePipeline.from_pretrained(
Expand All @@ -15,6 +16,12 @@
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)
pipe.load_lora(pipe.dit, "models/train/Qwen-Image-Layered-Control_lora/epoch-4.safetensors")

dataset_snapshot_download(
dataset_id="DiffSynth-Studio/example_image_dataset",
local_dir="./data/example_image_dataset",
allow_file_pattern="layer/image.png"
)
prompt = "Text 'HELLO' and 'Have a great day'"
input_image = Image.open("data/example_image_dataset/layer/image.png").convert("RGBA").resize((864, 480))
images = pipe(
Expand Down
7 changes: 7 additions & 0 deletions examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
from diffsynth import load_state_dict
from PIL import Image
import torch
from modelscope import dataset_snapshot_download


pipe = QwenImagePipeline.from_pretrained(
Expand All @@ -15,6 +16,12 @@
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)
pipe.load_lora(pipe.dit, "models/train/Qwen-Image-Layered_lora/epoch-4.safetensors")

dataset_snapshot_download(
dataset_id="DiffSynth-Studio/example_image_dataset",
local_dir="./data/example_image_dataset",
allow_file_pattern="layer/image.png"
)
prompt = "a poster"
input_image = Image.open("data/example_image_dataset/layer/image.png").convert("RGBA").resize((864, 480))
images = pipe(
Expand Down