GLM-Image

pip install git+https://github.com/huggingface/transformers.git
pip install git+https://github.com/huggingface/diffusers.git

import torch
from diffusers.pipelines.glm_image import GlmImagePipeline

pipe = GlmImagePipeline.from_pretrained("zai-org/GLM-Image", torch_dtype=torch.bfloat16, device_map="cuda")
prompt = "A beautifully designed modern food magazine style dessert recipe illustration, themed around a raspberry mousse cake. The overall layout is clean and bright, divided into four main areas: the top left features a bold black title 'Raspberry Mousse Cake Recipe Guide', with a soft-lit close-up photo of the finished cake on the right, showcasing a light pink cake adorned with fresh raspberries and mint leaves; the bottom left contains an ingredient list section, titled 'Ingredients' in a simple font, listing 'Flour 150g', 'Eggs 3', 'Sugar 120g', 'Raspberry puree 200g', 'Gelatin sheets 10g', 'Whipping cream 300ml', and 'Fresh raspberries', each accompanied by minimalist line icons (like a flour bag, eggs, sugar jar, etc.); the bottom right displays four equally sized step boxes, each containing high-definition macro photos and corresponding instructions, arranged from top to bottom as follows: Step 1 shows a whisk whipping white foam (with the instruction 'Whip egg whites to stiff peaks'), Step 2 shows a red-and-white mixture being folded with a spatula (with the instruction 'Gently fold in the puree and batter'), Step 3 shows pink liquid being poured into a round mold (with the instruction 'Pour into mold and chill for 4 hours'), Step 4 shows the finished cake decorated with raspberries and mint leaves (with the instruction 'Decorate with raspberries and mint'); a light brown information bar runs along the bottom edge, with icons on the left representing 'Preparation time: 30 minutes', 'Cooking time: 20 minutes', and 'Servings: 8'. The overall color scheme is dominated by creamy white and light pink, with a subtle paper texture in the background, featuring compact and orderly text and image layout with clear information hierarchy."
image = pipe(
    prompt=prompt,
    height=32 * 32,
    width=36 * 32,
    num_inference_steps=50,
    guidance_scale=1.5,
    generator=torch.Generator(device="cuda").manual_seed(42),
).images[0]

image.save("output_t2i.png")

import torch
from diffusers.pipelines.glm_image import GlmImagePipeline
from PIL import Image

pipe = GlmImagePipeline.from_pretrained("zai-org/GLM-Image", torch_dtype=torch.bfloat16, device_map="cuda")
image_path = "cond.jpg"
prompt = "Replace the background of the snow forest with an underground station featuring an automatic escalator."
image = Image.open(image_path).convert("RGB")
image = pipe(
    prompt=prompt,
    image=[image],  # can input multiple images for multi-image-to-image generation such as [image, image1]
    height=33 * 32, # Must set height even it is same as input image
    width=32 * 32, # Must set width even it is same as input image
    num_inference_steps=50,
    guidance_scale=1.5,
    generator=torch.Generator(device="cuda").manual_seed(42),
).images[0]

image.save("output_i2i.png")

pip install "sglang[diffusion] @ git+https://github.com/sgl-project/sglang.git#subdirectory=python"
pip install git+https://github.com/huggingface/transformers.git
pip install git+https://github.com/huggingface/diffusers.git

sglang serve --model-path zai-org/GLM-Image

curl http://localhost:30000/v1/images/generations \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org/GLM-Image",
    "prompt": "a beautiful girl with glasses.",
    "n": 1,
    "response_format": "b64_json",
    "size": "1024x1024"
  }' |  python3 -c "import sys, json, base64; open('output_t2i.png', 'wb').write(base64.b64decode(json.load(sys.stdin)['data'][0]['b64_json']))"

sglang serve --model-path zai-org/GLM-Image

curl -s -X POST "http://localhost:30000/v1/images/edits" \
-F "model=zai-org/GLM-Image" \
-F "image=@cond.jpg" \
-F "prompt=Replace the background of the snow forest with an underground station featuring an automatic escalator." \
-F "response_format=b64_json"  | python3 -c "import sys, json, base64; open('output_i2i.png', 'wb').write(base64.b64decode(json.load(sys.stdin)['data'][0]['b64_json']))"