Title: Loss of expressive variance and painterly instability in DALL·E 3 compared to earlier versions Category: Image generation / DALL·E I’d like to raise a concrete, technical concern regarding DALL·E 3 that affects professional artistic use, particularly in painterly and expressionist contexts…

[image] Bronko_Kulitschka: I’m happy to provide before/after examples if that’s helpful. Yes, that would be helpful. Include the prompt as well if you can.

Thanks, happy to provide examples. Prompt used (identical or near-identical across versions): Expressionist oil painting, heavy impasto, thick paint, visible and irregular brushstrokes, unstable forms, painterly abstraction, dynamic color fields, human imperfection, no photorealism, no smooth surf…

@Bronko_Kulitschka Note: The following was generated with the DALL-E-3 API and not ChatGPT - I’m not sure that ChatGPT can even create the DALL-E-3 images. It appears that both your images were not created by DALL-E-3. More than likely, they were created by gpt-image-1. Prompt: Image of a bearded…

Thanks for the clarification — this helps narrow it down. Based on the comparison, I think we’re actually observing two different behaviors: Older images (2023-era, ChatGPT image pipeline) show continuous, gestural stroke behavior: short directional strokes, overlap, irregular pressure, and visib…

Prompt: Create an image of a bearded man walking through a red light district in the style of Edvard Munch. [RedLight3] I think you can eventually get what you want using the right prompt with gpt-image-1.5. In many cases “over prompting“ leads to undesirable results. For example, your later prom…

Thanks for the example — it helps clarify the distinction I’m trying to make. I agree that using a Munch-style prompt reduces harshness and makes the image feel more painterly at first glance. However, the core issue I’m describing remains unchanged: The surface texture is still composed of short,…

With all due respect, I think you are being overly critical. Good luck.

Understood. My goal here wasn’t to debate whether the images are “good” or whether certain styles can be approximated. I was specifically documenting a change in stroke continuity and texture generation behavior compared to earlier outputs. I’ve provided examples and technical observations for that…

2025: [ChatGPT Image 9. Aug. 2025, 21_57_57]

Has DALL·E 3 lost expressive variance for painterly art?

ChatGPT Bugs

Bronko_Kulitschka January 24, 2026, 12:26pm 4

Later gen., 2026, not much creativity, industrial vectors, no art, only system-print:

Topic		Replies	Views
GPT Image is so dull and uninspiring vs Dall-E3 Community image-generation	9	6337	August 13, 2025
DALL-E 3: Opinionated, Boring Use cases and examples dalle3	36	29399	October 31, 2023
DALL-E 3's image generation quality no longer the same Bugs chatgpt , dalle3 , dalle3-bugs	10	1778	December 5, 2024
DALL-E 3 API images being much worse than ChatGPT API chatgpt , dalle3	5	4577	December 17, 2023
The Loss of Creative Freedom: A Struggle for My Art, Vision, and Character Evolution Use cases and examples gpt-4 , chatgpt	4	507	May 3, 2025

Has DALL·E 3 lost expressive variance for painterly art?

Related topics