diff --git a/data/reference-base.json b/data/reference-base.json index 70c3d8b58..88a1fb999 100644 --- a/data/reference-base.json +++ b/data/reference-base.json @@ -189,7 +189,7 @@ "path": "CalamitousFelicitousness/Krea-2-Base-Diffusers", "preview": "CalamitousFelicitousness--Krea-2-Base-Diffusers.jpg", "desc": "Krea 2 (K2) Base is the undistilled foundation model of the Krea 2 family, trained from scratch by Krea. A 12.9B-parameter single-stream flow-matching DiT that uses a Qwen3-VL-4B vision-language model as its text encoder and the Qwen-Image VAE. The base checkpoint is intended for fine-tuning and LoRA training; LoRAs trained on it apply to Krea 2 Turbo.", - "extras": "sampler: Default, cfg_scale: 4.5, steps: 52, width: 1024, height: 1024", + "extras": "sampler: Default, cfg_scale: 4.5, steps: 52", "size": 33.5, "date": "2026 June" }, diff --git a/data/reference-distilled.json b/data/reference-distilled.json index f1391ec63..bbd37191e 100644 --- a/data/reference-distilled.json +++ b/data/reference-distilled.json @@ -26,7 +26,7 @@ "path": "CalamitousFelicitousness/Krea-2-Turbo-Diffusers", "preview": "CalamitousFelicitousness--Krea-2-Turbo-Diffusers.jpg", "desc": "Krea 2 (K2) Turbo is the 8-step distilled inference model of the Krea 2 family, trained from scratch by Krea. A 12.9B-parameter single-stream flow-matching DiT that uses a Qwen3-VL-4B vision-language model as its text encoder and the Qwen-Image VAE. Runs without classifier-free guidance; LoRAs trained on Krea 2 Base apply directly.", - "extras": "sampler: Default, cfg_scale: 1.0, steps: 8, width: 1024, height: 1024", + "extras": "sampler: Default, cfg_scale: 1.0, steps: 8", "size": 33.5, "date": "2026 June" }, @@ -129,7 +129,7 @@ "path": "SDXL-Flash_Mini.safetensors@https://huggingface.co/sd-community/sdxl-flash-mini/resolve/main/SDXL-Flash_Mini.safetensors?download=true", "preview": "SDXL-Flash_Mini.jpg", "desc": "Introducing the new fast model SDXL Flash (Mini), we learned that all fast XL models work fast, but the quality decreases, and we also made a fast model, but it is not as fast as LCM, Turbo, Lightning and Hyper, but the quality is higher.", - "extras": "width: 2048, height: 1024, sampler: DEIS, steps: 40, cfg_scale: 6.0", + "extras": "sampler: DEIS, steps: 40, cfg_scale: 6.0", "experimental": true }, "NVLabs Sana 1.5 1.6B 1k Sprint": { diff --git a/data/reference-quantized.json b/data/reference-quantized.json index c544542a6..92267b09c 100644 --- a/data/reference-quantized.json +++ b/data/reference-quantized.json @@ -230,7 +230,7 @@ "path": "vladmandic/Krea-2-Turbo-sdnq-hadamard-uint4", "preview": "CalamitousFelicitousness--Krea-2-Turbo-Diffusers.jpg", "desc": "Krea 2 (K2) Turbo is the 8-step distilled inference model of the Krea 2 family, trained from scratch by Krea. A 12.9B-parameter single-stream flow-matching DiT that uses a Qwen3-VL-4B vision-language model as its text encoder and the Qwen-Image VAE. Runs without classifier-free guidance; LoRAs trained on Krea 2 Base apply directly.", - "extras": "sampler: Default, cfg_scale: 1.0, steps: 8, width: 1024, height: 1024", + "extras": "sampler: Default, cfg_scale: 1.0, steps: 8", "size": 10.54, "date": "2026 July" }, @@ -238,7 +238,7 @@ "path": "vladmandic/Krea-2-Base-sdnq-hadamard-uint4", "preview": "CalamitousFelicitousness--Krea-2-Base-Diffusers.jpg", "desc": "Krea 2 (K2) Base is the undistilled foundation model of the Krea 2 family, trained from scratch by Krea. A 12.9B-parameter single-stream flow-matching DiT that uses a Qwen3-VL-4B vision-language model as its text encoder and the Qwen-Image VAE. The base checkpoint is intended for fine-tuning and LoRA training; LoRAs trained on it apply to Krea 2 Turbo.", - "extras": "sampler: Default, cfg_scale: 4.5, steps: 52, width: 1024, height: 1024", + "extras": "sampler: Default, cfg_scale: 4.5, steps: 52", "size": 10.3, "date": "2026 June" } diff --git a/modules/ui_definitions.py b/modules/ui_definitions.py index 2a38277dd..3e5d11572 100644 --- a/modules/ui_definitions.py +++ b/modules/ui_definitions.py @@ -150,7 +150,7 @@ def create_settings(cmd_opts): "caption_offload": OptionInfo(True, "Offload caption models"), "caption_to_gpu": OptionInfo(True, "Load caption models direct to GPU"), "offload_balanced_sep": OptionInfo("

Balanced Offload

", "", gr.HTML), - "diffusers_offload_pre": OptionInfo(True, "Offload during pre-forward"), + "diffusers_offload_pre": OptionInfo(True, "Offload during pre-forward", gr.Checkbox, {"visible": False}), "diffusers_offload_streams": OptionInfo(False, "Offload using streams"), "diffusers_offload_min_gpu_memory": OptionInfo(startup_offload_min_gpu, "Offload low watermark", gr.Slider, {"minimum": 0, "maximum": 1, "step": 0.01 }), "diffusers_offload_max_gpu_memory": OptionInfo(startup_offload_max_gpu, "Offload GPU high watermark", gr.Slider, {"minimum": 0.1, "maximum": 1, "step": 0.01 }),