Downloads · 30 days
27
31% of all-time downloads
mash2005/Qwen-Image-Edit-2511-MultiAngles-FullQ4
Qwen-Image-Edit-2511-MultiAngles-FullQ4 is a image-to-image model from mash2005. Use it when you need one image transformed into another. It is set up for diffusers.
basemodel: Qwen/Qwen-Image-Edit-2511 libraryname: diffusers license: apache-2.0 tags: - qwen-image-edit - lora - multi-angle - camera-angles - image-to-image - quantized - nf4 ---
Downloads · 30 days
27
31% of all-time downloads
All-time downloads
87
Public
Parameters
10.5B
16.7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.7 GB · 100%
How the weights are stored.
U810.5B · 100%
From the Hugging Face model README
base_model: Qwen/Qwen-Image-Edit-2511 library_name: diffusers license: apache-2.0 tags:
Merged and fully quantized version of Qwen/Qwen-Image-Edit-2511 with fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA fused into the weights.
Both the DiT transformer and the Qwen2.5-VL text encoder are quantized to NF4 4-bit with double quantization. Runs on ~15GB VRAM — fits a T4.
import torch
from diffusers import QwenImageEditPlusPipeline, QwenImageTransformer2DModel
from transformers import Qwen2_5_VLForConditionalGeneration, BitsAndBytesConfig
from PIL import Image
quant_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16,
bnb_4bit_use_double_quant=True,
)
transformer = QwenImageTransformer2DModel.from_pretrained(
"mash2005/Qwen-Image-Edit-2511-MultiAngles-FullQ4",
subfolder="transformer",
torch_dtype=torch.bfloat16,
device_map="cuda"
)
text_encoder = Qwen2_5_VLForConditionalGeneration.from_pretrained(
"mash2005/Qwen-Image-Edit-2511-MultiAngles-FullQ4",
subfolder="text_encoder",
torch_dtype=torch.bfloat16,
device_map="cuda"
)
pipeline = QwenImageEditPlusPipeline.from_pretrained(
"mash2005/Qwen-Image-Edit-2511-MultiAngles-FullQ4",
transformer=transformer,
text_encoder=text_encoder,
torch_dtype=torch.bfloat16,
)
pipeline.enable_model_cpu_offload()
image = Image.open("your_image.jpg").convert("RGB")
result = pipeline(
image=[image],
prompt="Show this object from the back view, azimuth 180 degrees",
negative_prompt=" ",
num_inference_steps=30,
guidance_scale=1.0,
true_cfg_scale=4.0,
).images[0]
result.save("output.png")
"front view, azimuth 0 degrees""back view, azimuth 180 degrees""side view, azimuth 90 degrees""top-down view, elevation 90 degrees"