Hello
Getting same black image without LORA
Python & Torch Details:
(venv) D:\Ganu\AIImage\project\Train-10Images-chatgptParameters\runs\1sstrun-23thApril2025\generation\1stGo>python
Python 3.10.10 (tags/v3.10.10:aad5f6a, Feb 7 2023, 17:20:36) [MSC v.1929 64 bit (AMD64)] on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>>
>>> # Check if torch was built with CUDA
>>> print("Is CUDA available? :", torch.cuda.is_available())
Is CUDA available? : True
>>> print("CUDA version (torch compiled with):", torch.version.cuda)
CUDA version (torch compiled with): 11.8
>>> print("Torch built with CUDA support:", torch.backends.cuda.is_built())
Torch built with CUDA support: True
Code:
import logging
from diffusers import AutoPipelineForText2Image, AutoencoderKL
import torch
import numpy as np
import random
import os
from PIL import Image
# =========================
# STEP 0: Logging Setup
# =========================
log_file = "generation_log.txt"
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(levelname)s - %(message)s',
handlers=[
logging.FileHandler(log_file),
logging.StreamHandler()
]
)
logging.info("Initializing...")
# =========================
# STEP 1: Environment Setup
# =========================
torch.cuda.empty_cache()
torch.cuda.ipc_collect()
seed = random.randint(0, 9999999)
torch.manual_seed(seed)
np.random.seed(seed)
logging.info(f"Using seed: {seed}")
# ===============================
# STEP 2: Model and LoRA Setup
# ===============================
logging.info("Loading base model and LoRA weights...")
model_dir = "D:\\Ganu\\AIImage\\huggingface\\kohya_ss\\kohya_ss\\outputs"
lora_weights_path = os.path.join(model_dir, "model")
model_id = "stabilityai/stable-diffusion-xl-base-1.0"
# Optional: Custom VAE (uncomment if needed)
vae = AutoencoderKL.from_pretrained(
"madebyollin/sdxl-vae-fp16-fix",
torch_dtype=torch.float16
).to("cuda")
try:
pipeline = AutoPipelineForText2Image.from_pretrained(
model_id,
torch_dtype=torch.float16,
variant="fp16",
).to("cuda")
logging.info("Pipeline loaded to GPU with float16.")
except Exception as e:
logging.error(f"Failed to load model pipeline: {e}")
raise
#pipeline.enable_model_cpu_offload()
# If using VAE:
pipeline.vae = vae
pipeline.enable_attention_slicing()
pipeline.enable_vae_slicing()
"""try:
pipeline.load_lora_weights(lora_weights_path, weight_name="last.safetensors")
logging.info("LoRA weights loaded successfully.")
except ValueError as e:
logging.error("Invalid LoRA checkpoint. Check the format or compatibility.")
raise e
"""
# =========================
# STEP 3: Prompt Inference
# =========================
text_prompt = (
"A wide, breathtaking landscape with all real vibrant nature-themed background, lush forests, mountains, and a Doctor standing prominently in the foreground"
)
negative_prompt = (
"text, letters, words, signage, logos, labels, writing, messy background, busy layout, clutter, double faces, abstract shapes, UI panels with words, overlapping elements, header, footer, top bar, navigation bar, bottom menu, toolbar, top text, website layout, browser frame, button row, page border, UI bar"
)
logging.info(f"Running inference with prompt: {text_prompt}")
try:
result = pipeline(
prompt=text_prompt,
negative_prompt=negative_prompt,
guidance_scale=7.5,
num_inference_steps=30
)
generated_image = result.images[0]
output_path = f"generated_image_{seed}.png"
generated_image.save(output_path)
logging.info(f"Image saved to: {output_path}")
generated_image.show()
except Exception as e:
logging.error(f"Error during image generation: {e}")
raise
Environment:
1. Libraries
pip list
Package Version
------------------ ------------------
accelerate 0.21.0
aiofiles 24.1.0
annotated-types 0.7.0
anyio 4.9.0
certifi 2025.1.31
charset-normalizer 3.4.1
click 8.1.8
colorama 0.4.6
deepspeed 0.10.0+f5c834a6
diffusers 0.21.4
exceptiongroup 1.2.2
fastapi 0.115.12
ffmpy 0.5.0
filelock 3.18.0
flash-attention 1.0.0
fsspec 2025.3.2
gradio 5.27.1
gradio_client 1.9.1
groovy 0.1.2
h11 0.16.0
hjson 3.1.0
httpcore 1.0.9
httpx 0.28.1
huggingface-hub 0.16.4
idna 3.10
importlib_metadata 8.6.1
Jinja2 3.1.6
markdown-it-py 3.0.0
MarkupSafe 3.0.2
mdurl 0.1.2
mpmath 1.3.0
mypy_extensions 1.1.0
networkx 3.4.2
ninja 1.11.1.4
numpy 1.23.1
orjson 3.10.16
packaging 25.0
pandas 2.2.3
peft 0.15.2
pillow 11.2.1
pip 25.1.1
psutil 7.0.0
py-cpuinfo 9.0.0
pydantic 1.10.13
pydantic_core 2.33.1
pydub 0.25.1
Pygments 2.19.1
pyre-extensions 0.0.29
python-dateutil 2.9.0.post0
python-multipart 0.0.20
pytz 2025.2
PyYAML 6.0.2
regex 2024.11.6
requests 2.32.3
rich 14.0.0
ruff 0.11.7
safehttpx 0.1.6
safetensors 0.5.3
semantic-version 2.10.0
setuptools 65.5.0
shellingham 1.5.4
six 1.17.0
sniffio 1.3.1
starlette 0.46.2
sympy 1.14.0
tokenizers 0.13.3
tomlkit 0.13.2
torch 2.4.0+cu118
torchaudio 2.7.0+cu118
torchvision 0.22.0+cu118
tqdm 4.67.1
transformers 4.31.0
typer 0.15.3
typing_extensions 4.13.2
typing-inspect 0.9.0
typing-inspection 0.4.0
tzdata 2025.2
urllib3 2.4.0
uvicorn 0.34.2
websockets 15.0.1
xformers 0.0.27.post2+cu118
zipp 3.21.0
- nvdia-sim output
(venv) D:\Ganu\AIImage\project\Train-10Images-chatgptParameters\runs\1sstrun-23thApril2025\generation\1stGo>nvidia-smi
Thu May 15 14:36:50 2025
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 576.40 Driver Version: 576.40 CUDA Version: 12.9 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Driver-Model | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce GTX 1650 WDDM | 00000000:01:00.0 On | N/A |
| N/A 47C P8 5W / 50W | 698MiB / 4096MiB | 3% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 5648 C+G ...IA app\CEF\NVIDIA Overlay.exe N/A |
| 0 N/A N/A 6664 C+G ...we\Microsoft.Media.Player.exe N/A |
| 0 N/A N/A 7348 C+G ...Chrome\Application\chrome.exe N/A |
| 0 N/A N/A 7560 C+G ...Chrome\Application\chrome.exe N/A |
| 0 N/A N/A 7940 C+G ....0.3240.64\msedgewebview2.exe N/A |
| 0 N/A N/A 9104 C+G C:\Windows\explorer.exe N/A |
| 0 N/A N/A 9520 C+G ...h_cw5n1h2txyewy\SearchApp.exe N/A |
| 0 N/A N/A 9728 C+G ...ntrolPanel\SystemSettings.exe N/A |
| 0 N/A N/A 11968 C+G ...h_cw5n1h2txyewy\SearchApp.exe N/A |
| 0 N/A N/A 14064 C+G ...5n1h2txyewy\TextInputHost.exe N/A |
| 0 N/A N/A 15292 C+G ...IA app\CEF\NVIDIA Overlay.exe N/A |
+-----------------------------------------------------------------------------------------+