Upload folder using huggingface_hub

.gitattributes

@@ -33,4 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/teaser.png filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -6,6 +6,7 @@ license_link: LICENSE
 
 # Model Overview
 
+
 ## Description
 
 NL-Diffusion-Image introduces a new paradigm for high-resolution text-to-image generation via LLM based on masked discrete diffusion over tokenized image patches.
@@ -17,6 +18,8 @@ We finetune from [Nemotron-Labs-Diffusion](https://huggingface.co/nvidia/Nemotro
 
 This model is ready for research or non-commercial evaluation.
 
+
+![Teaser Image](assets/teaser.png)
 ### License/Terms of Use
 
 GOVERNING TERMS: Use of this model is governed by the [NVIDIA Open Source License Agreement](https://huggingface.co/nvidia/NL-Diffusion-Image/raw/main/LICENSE).
@@ -298,3 +301,54 @@ Model Application Field(s):                               |  Generation of image
 Describe the life critical impact (if present).   |  Not Applicable
 Use Case Restrictions:                              |  Research/evaluation only, non-commercial applications.
 Model and dataset restrictions:            |  The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to.
+
+
+## Quick Start 
+
+```
+import torch
+from transformers import AutoModelForCausalLM, PreTrainedTokenizerFast
+
+model_path = "shufanlNvidia/NLD-Diffusion-Image-8B-Internal"
+tokenizer = PreTrainedTokenizerFast.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    trust_remote_code=True,
+    torch_dtype=torch.bfloat16,
+)
+model = model.to("cuda").eval()
+model.config.dlm_paradigm = "bidirectional"
+PROMPT = (
+    "A full-body shot of hyper-realistic female cyborg, human facial skin seamlessly integrated with a glossy white mechanical head shell. "
+    "Features a realistic human ear, blue eyes. bright, outdoor, background with blue sky, illuminated by striking bright white studio lighting, "
+    "casting soft shadows. Cyberpunk aesthetic, high-tech minimalism, shot on 85mm lens, photorealistic, Unreal Engine 5 render, intricately detailed, "
+    "8k resolution, high dynamic range, chest with whit armor plate, cute, beautiful, sexy, glossy surface, reflective, Artstation, pixiv, no hair, "
+    "3D render, stylized eyesz"
+)
+torch.manual_seed(42)
+
+image = model.text_to_image(
+    PROMPT,
+    tokenizer=tokenizer,
+    image_resolution=1024,
+    n_tokens=(1024 // 16) * (1024 // 16),
+    guidance_scale=5.0,
+    temperature=0.86,
+    n_steps=64,
+    schedule="shift",
+    shift=5,
+    confidence_policy="mmada",
+    schedule_temp="linear",
+    alg_temp=1.0,
+    dynamic_temperature=False,
+    min_temperature=0.01,
+    edit_threshold=0.6,
+    micro_cond="ORIGINAL WIDTH : 1024; ORIGINAL HEIGHT : 1024; TOP : 0; LEFT : 0; SCORE : 6.520; HPS: 3.220",
+    block_policy=2,
+    is_legacy=False,
+    use_cache=False,
+)
+image.save("output.webp")
+```
+
+See [demo_inference_release.py](demo_inference_release.py) for more details of inference arguments.

demo_inference_release.py

@@ -9,7 +9,7 @@ from transformers import AutoModelForCausalLM, PreTrainedTokenizerFast
 os.environ.setdefault("DEBUG_FIX_PADDING", "1")
 os.environ.setdefault("NOT_ALWASY_DO_2DPOOL", "1")
 
-DEFAULT_CKPT = "/lustre/fsw/portfolios/nvr/users/shufanl/projects/ministral-output/nemotron-labs-diffuion-image-8B-release"
+DEFAULT_CKPT = "/path/to/nemotron-labs-diffuion-image-8B-release"
 DEFAULT_PROMPT = (
     "A full-body shot of hyper-realistic female cyborg, human facial skin seamlessly integrated with a glossy white mechanical head shell. "
     "Features a realistic human ear, blue eyes. bright, outdoor, background with blue sky, illuminated by striking bright white studio lighting, "
@@ -17,7 +17,7 @@ DEFAULT_PROMPT = (
     "8k resolution, high dynamic range, chest with whit armor plate, cute, beautiful, sexy, glossy surface, reflective, Artstation, pixiv, no hair, "
     "3D render, stylized eyesz"
 )
-DEFAULT_OUTPUT = "/lustre/fsw/portfolios/nvr/users/shufanl/code/LaVida-O/outputs/demo_inference_release.webp"
+DEFAULT_OUTPUT = "/path/to/output/demo_inference_release.webp"
 
 SCHEDULE_CHOICES = ["shift"]
 CONFIDENCE_POLICY_CHOICES = ["mask_git", "mmada", "stratified"]