Add model-specific OrbitQuant usage examples

README.md

@@ -20,7 +20,7 @@ Install the package from this repository, then load the base pipeline and patch
 
 ```python
 import torch
-from diffusers import DiffusionPipeline
+from diffusers import ZImagePipeline
 from huggingface_hub import snapshot_download
 from orbitquant import load_quantized_pipeline_component
 
@@ -28,7 +28,7 @@ base_model = "Tongyi-MAI/Z-Image-Turbo"
 artifact_id = "WaveCut/Z-Image-Turbo-OrbitQuant-W2A4"
 
 artifact_dir = snapshot_download(artifact_id, repo_type="model")
-pipe = DiffusionPipeline.from_pretrained(
+pipe = ZImagePipeline.from_pretrained(
     base_model,
     torch_dtype=torch.bfloat16,
 )
@@ -40,13 +40,16 @@ load_quantized_pipeline_component(
 )
 pipe.to("cuda")
 
-result = pipe(
+image = pipe(
     prompt="A precise product photo of a red ceramic mug on a wooden desk",
-)
+    height=1024,
+    width=1024,
+    num_inference_steps=10,
+    guidance_scale=0.0,
+).images[0]
+image.save("z-image-orbitquant.png")
 ```
 
-For model-specific pipelines, you may replace `DiffusionPipeline` with the matching Diffusers class, such as `FluxPipeline`, `Flux2KleinPipeline`, `ZImagePipeline`, or `WanPipeline` when your Diffusers version provides it.
-
 ## Quantization
 
 - Method: `orbitquant`
@@ -73,14 +76,14 @@ For model-specific pipelines, you may replace `DiffusionPipeline` with the match
 
 The following assets are stored in this artifact and compare the BF16 base generation against the OrbitQuant generation with the same prompt and seed.
 
+![reports/native/z-image-w2a4-1348cb6/assets/image_generation_comparison_matrix.webp](reports/native/z-image-w2a4-1348cb6/assets/image_generation_comparison_matrix.webp)
+
 ![assets/original_vs_orbitquant_z-image-native_seed0_W2A4_color-binding.webp](assets/original_vs_orbitquant_z-image-native_seed0_W2A4_color-binding.webp)
 
 ![assets/original_vs_orbitquant_z-image-native_seed0_W2A4_counting.webp](assets/original_vs_orbitquant_z-image-native_seed0_W2A4_counting.webp)
 
 ![assets/original_vs_orbitquant_z-image-native_seed0_W2A4_cyrillic-text-rendering.webp](assets/original_vs_orbitquant_z-image-native_seed0_W2A4_cyrillic-text-rendering.webp)
 
-![assets/original_vs_orbitquant_z-image-native_seed0_W2A4_english-text-rendering.webp](assets/original_vs_orbitquant_z-image-native_seed0_W2A4_english-text-rendering.webp)
-
 ## Source
 
 - Model: `Tongyi-MAI/Z-Image-Turbo`

SHA256SUMS

@@ -1,4 +1,4 @@
-7b22614723a9322935b2c9af7bab35bbef5c24489b06dfdba2101ee78ecb4de9  README.md
+2a530f5e53e1f01a91d11263bcd7659a4016a14f3d14acaee1263ccb6da86749  README.md
 e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855  assets/.gitkeep
 8c8731e445b7cefae4b0fb1aa5c716bc01b2c91f67e34d46bf6afc40a02aec0f  assets/original_vs_orbitquant_z-image-native_seed0_W2A4_color-binding.webp
 4a58042eadc55289dd18b1c0841e95dbd9a3f7ba4fa63178af43bfe4918ed8db  assets/original_vs_orbitquant_z-image-native_seed0_W2A4_counting.webp