IC-1202Stable Diffusion 1.5 and 2.1 exhibit a cropping failure mode where synthesized objects are cut off at image boundaries

Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas Müller, Joe Penna, Robin Rombach

SourceSDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

The paper identifies a reproducible failure mode in SD 1.5 and SD 2.1: generated objects appear cropped or truncated at the edges of the image (e.g., a cat's head cut off). The authors attribute this to random cropping used during training as a data augmentation step, which leaks into the generation process. SDXL addresses this by conditioning on crop coordinates, and the paper shows that SDXL does not exhibit this artifact under the same prompts.

Evidence
observational
Caveat
The paper shows 3 random samples per model per prompt (Fig. 4); the failure is described as 'typical' but no systematic rate is quantified.
Model
Stable Diffusion 1.5, 2.1
Concepts
Failure mode
Related findings
IC-1203, IC-1204
Extraction
automatic-extraction