Size Qwen 2.1 Generate from the bench aspect table.

Wire EmptyLatentImage to the official ~1 MP grid so 16:9 lands at 1536×864, keep PE wh_ratio advisory, and leave Edit on the encode latent from image_1.

Co-authored-by: Cursor <cursoragent@cursor.com>

docs/qwen21.md

@@ -38,7 +38,8 @@ Restart Comfy **only when idle** (`COMFY_CONTROL_URL/status` → `gpu.busy=false
 - Edit requires Start still → `images.image_1`; prompt slots use `<image1>` / `<image2>`. If the user omits `<image1>`, the runner prepends `Keep the subject in <image1>.`
 - Face / outfit locks stay Klein semantics — they do not drive Qwen slots.
 - Sampler defaults: euler / simple / cfg **1** / steps **25**. Edit uses `QwenImage21Cache` (device auto, dtype int8). T2I uses `ModelSamplingAuraFlow` shift **3.1**.
-- Default canvas **1024×1024** (aspect 16:9 / 9:16 / 1:1 → long-edge ~1024 via `TextEncodeQwenImage21` resolution; multiples of 32). Edit with aspect `auto` follows `image_1` aspect at ~1024.
+- Default Generate canvas follows the bench Aspect control on the Qwen-safe ~1 MP grid (`EmptyLatentImage`): 1:1 → 1024×1024, 16:9 → 1536×864, 9:16 → 864×1536 (and the other table rows). PE `wh_ratio` is advisory only and never sizes the canvas. Do not use native 2K bins on 16 GB.
+- Edit follows `image_1` via the encode node’s latent (resolution long-edge ~1024). Do not inject a picker EmptyLatentImage onto the edit sampler.
 - Optional **Enhance prompt** (off by default): runs a separate PE-only Comfy graph (`CLIPLoader` + rewrite node), then frees VRAM and queues the existing T2I/Edit graph with the rewritten prompt. Never loads PE CLIP + DiT together on 16 GB. Fail closed if `parse_ok` is false or the rewrite is empty.
 - PE weights (int8 only): `text_encoders\qwen3.5_9b_qwen_image_2.1_pe_{t2i,i2i}.int8_convrot.safetensors` — do not replace the image TE `qwen3vl_8b_int8_convrot.safetensors`.
 - Custom node: `ComfyUI-Qwen-Image-2.1-Prompt-Enhancer` (`QwenImage21_T2IPromptRewrite` / `QwenImage21_EditPromptRewrite`).