The hardest part of content creation: expressive faces for YouTube thumbnails
jackedAJ · x · 2026-09-23
A content creator says generating expressive, exaggerated faces for YouTube thumbnails is the hardest part of his workflow with AI, calling it "hard and weird" and sharing a generated example — highlighting a persistent weakness in image models for strong emotional expressions.
More from Multimodal
- Tencent Hunyuan Image 3.5 preview lands on OnSolo, free for two weeks — TencentHunyuan · 2026-09-23
- Testing invideo's AI editor: one prompt, and the agent reworks the whole trailer's sound design — LudovicCreator · 2026-09-23
- Tencent Hunyuan open-sources AuK audio model, drawing speed raves — bingxu_ · 2026-09-23
- 192-image side-by-side benchmark: Qwen Image 2.1 vs Krea 2 — dh7net · 2026-09-23
- Kling Motion Control enables near-free character swaps, shaking up Hollywood — Aiden_Tech_Ai · 2026-09-23
- Music video made by Opus 5.5: 'You are Gaspode' pays tribute to Pratchett's talking dog — repligate · 2026-09-23