{ "id": "qwen-turbo-09", "label": "Qwen Image 2.1 Turbo Q4_K_M · New brief, retained model runtime · seed 50", "group": "qwen21-turbo-q4km-ten", "kind": "image", "model_id": "qwen-turbo", "model": "unsloth/Qwen-Image-2.1-Turbo-GGUF:Q4_K_M", "seed": 50, "status": "succeeded", "accepted_result": true, "prompt": "A detailed travel photograph of a lively Mediterranean open-air produce market in early morning. In the foreground, three wooden crates hold red tomatoes, striped eggplants and yellow lemons, each type kept in its own crate. An adult vendor wearing a plain white shirt stands behind the stall, handing a small paper bag to an adult customer in a green jacket. A striped blue-and-white canopy casts cool shade over the stall. Beyond them, a narrow pedestrian street slopes toward a distant harbor with two white sailboats. Warm sunlight touches the upper walls but the foreground remains softly shaded. Compose the scene in layers with natural human proportions, believable hands, clear separation between people, baskets and produce, and rich but realistic color. Avoid artificial lens flares, watermarks and unreadable signs.", "prompt_details": { "word_count": 128, "complexity": "Crowded composition", "conditioning_texts": { "3.prompt": "Create a single image from the supplied scene description.\n\nSource generation_brief:\nA detailed travel photograph of a lively Mediterranean open-air produce market in early morning. In the foreground, three wooden crates hold red tomatoes, striped eggplants and yellow lemons, each type kept in its own crate. An adult vendor wearing a plain white shirt stands behind the stall, handing a small paper bag to an adult customer in a green jacket. A striped blue-and-white canopy casts cool shade over the stall. Beyond them, a narrow pedestrian street slopes toward a distant harbor with two white sailboats. Warm sunlight touches the upper walls but the foreground remains softly shaded. Compose the scene in layers with natural human proportions, believable hands, clear separation between people, baskets and produce, and rich but realistic color. Avoid artificial lens flares, watermarks and unreadable signs." }, "actual_positive_text": "Create a single image from the supplied scene description.\n\nSource generation_brief:\nA detailed travel photograph of a lively Mediterranean open-air produce market in early morning. In the foreground, three wooden crates hold red tomatoes, striped eggplants and yellow lemons, each type kept in its own crate. An adult vendor wearing a plain white shirt stands behind the stall, handing a small paper bag to an adult customer in a green jacket. A striped blue-and-white canopy casts cool shade over the stall. Beyond them, a narrow pedestrian street slopes toward a distant harbor with two white sailboats. Warm sunlight touches the upper walls but the foreground remains softly shaded. Compose the scene in layers with natural human proportions, believable hands, clear separation between people, baskets and produce, and rich but realistic color. Avoid artificial lens flares, watermarks and unreadable signs." }, "parameters": { "1 UnetLoaderGGUFAdvanced": { "unet_name": "qwen-image-2.1-turbo-Q4_K_M.gguf", "dequant_dtype": "float32", "patch_dtype": "float32", "patch_on_device": false }, "2 CLIPLoader": { "clip_name": "qwen3vl_8b_int8_convrot.safetensors", "type": "qwen_image", "device": "cpu" }, "3 TextEncodeQwenImage21": { "negative_prompt": "", "resolution": 512 }, "4 VAELoader": { "vae_name": "qwen_image_2.1_vae_bf16.safetensors" }, "5 QwenImage21Cache": { "device": "off", "dtype": "default" }, "6 SamplerCustomAdvanced": {}, "7 VAEDecode": {}, "8 SaveImage": {}, "9 RandomNoise": { "noise_seed": 50 }, "10 CFGGuider": { "cfg": 1.0 }, "11 KSamplerSelect": { "sampler_name": "euler" }, "12 ManualSigmas": { "sigmas": "1.0, 0.978453, 0.95418, 0.926626, 0.89508, 0.845148, 0.704534, 0.414568, 0" } }, "timing": { "factory_trace_seconds": 210.965741, "comfy_server_seconds": 208.566, "stages_seconds": { "node_3_observer_receive_interval": 107.82800000003772, "node_10_observer_receive_interval": 0, "node_9_observer_receive_interval": 0, "node_6_observer_receive_interval": 72.20299999997951, "node_7_observer_receive_interval": 28.43800000002375, "node_8_observer_receive_interval": 0.061999999976251274 }, "limits": "Native server boundaries, factory attempt traces and observed delivery have different timing scopes. Observer node intervals include loading/preparation/event delivery, not isolated kernel or weight-only times." }, "cache": { "cached_nodes": [ "1", "11", "12", "2", "4", "5" ], "same_runtime_retained": true, "immediate_warm_claim": false, "encoder_cached": false, "context": { "workload": "New brief, retained model runtime", "native_inter_run_gap_seconds": 13.101, "only_seed_changed_from_predecessor": false, "text_changed_from_predecessor": true, "cold_start_scope": null } }, "resources": { "sampled_summary": { "sample_count": 103, "inflight_sample_count": 102, "minimum_ram_available_bytes": 4364185600, "minimum_commit_available_bytes": 11356860416, "minimum_system_drive_free_bytes": 18670198784, "maximum_sampled_device_gpu_used_mib": 4351 }, "limits": "Device-wide GPU observations include display and other workloads. These sampled extrema do not establish dedicated-VRAM residency or absence of shared-memory paging." }, "encoding": { "encoder_cached": false, "token_truncation_verified": false, "interpretation": "Exact Qwen encoder token truncation was not instrumented. The complete actual composed conditioning text is retained." }, "verification": { "full_decode": true, "checksum": true, "acknowledged": true, "trace_attachment": true, "native_experiment": true, "independent_public_copy_decode": true, "visual_review": true, "quality_scope": "Independent subjective inspection of the original 512×512 PNG; no scored quality benchmark and no causal attribution to quantization or schedule." }, "findings": [ "Recognizable market transaction under a striped canopy, with three separate produce crates and a harbor beyond. Main scene layers are coherent.", "White-shirt vendor, green-jacket customer, blue-and-white canopy, separate tomatoes/eggplants/lemons and sunlit upper wall over shaded foreground are all present. The paper bag and precise handoff are visually ambiguous. Harbor sailboats are visible but the exact requested count of two is not certifiable at this size.", "Vegetables, wood, clothing and canopy fabric are distinguishable. Fine background detail is smeared/brushy despite a photographic brief.", "Main adult body proportions look plausible. The central touching hands are soft and partially merged/occluded; finger anatomy and grasp cannot be verified. Background masts and architecture become muddled.", "No prominent legible sign, watermark or caption appears.", "Paper-bag handoff is less clear than requested.", "Hands and distant harbor details are imprecise.", "Exact two-sailboat count remains uncertain." ], "media": [ { "path": "media/qwen-turbo-09.png", "mime_type": "image/png", "size_bytes": 437788, "sha256": "847ec6dd9be4503a94967f96ca4b91d223ffb7638749c4fd08fb318723f544e0", "source_sha256": "5b992fa647b0461c1eb8514854a32b5f44cdd297a129a110f72b1abff6a830ef", "width": 512, "height": 512, "pixel_sha256": "ffaa52b367e79221e07aeed4066dcadc2039859372848f38c9bc028d623b7f50", "metadata_handling": "PNG re-encoded losslessly without ancillary metadata; decoded pixels unchanged.", "public_copy_full_decode_passed": true, "source_content_preserved": "Decoded pixels byte-identical" } ], "workflow_path": "workflows/qwen-turbo-09.json", "workflow_sha256": "049b53d4c92125dbe083563cea3d836330cfd864f19317933f71cb8794bc7db6", "source_workflow_canonical_sha256": "e1fd339039ed8d1dde53d4a0668665f4b78470cce872ff0c3f831156539dd328" }