Example notes: say what the graph does

- Krea 2 Inpaint Masked: the saved-by-name copies of two notes now
  match the positional text.
- Krea 2 Rotate + Outpaint: the note describes the tone match the
  graph runs.
- Qwen Image 2.1 Inpaint: the note says the seed is fixed.
- Qwen Image 2.1 Upscale + Restore: the Megapixels note mentions the
  roughly 2 MP minimum redraw.

example_workflows/Krea 2 Inpaint Masked (AusBoss).json

@@ -1913,7 +1913,7 @@
               "The painted area, grown a little, is filled with flat gray, so Krea 2 knows where to paint. The plain crop goes along too."
             ],
             "widgets_values_named": {
-              "text": "The painted area, grown a little, is filled with flat gray. Krea 2 never sees what you are replacing."
+              "text": "The painted area, grown a little, is filled with flat gray, so Krea 2 knows where to paint. The plain crop goes along too."
             },
             "color": "#1f2c38",
             "bgcolor": "#2a3b4a"
@@ -3052,7 +3052,7 @@
               "The gray-filled crop is the reference. Painting starts from the plain crop, inside the noise mask: the painted area, widened by 24 px."
             ],
             "widgets_values_named": {
-              "text": "The gray-filled crop is the reference. The noise mask is the grown painted area, widened by 24 px. Krea 2 paints only inside it."
+              "text": "The gray-filled crop is the reference. Painting starts from the plain crop, inside the noise mask: the painted area, widened by 24 px."
             },
             "color": "#1f2c38",
             "bgcolor": "#2a3b4a"

example_workflows/Krea 2 Rotate + Outpaint (AusBoss).json

@@ -2139,10 +2139,10 @@
             "title": "Note",
             "properties": {},
             "widgets_values": [
-              "Blend in fades the model's picture into yours just inside its edge, with no tone shift. The new area stays as painted."
+              "Blend in fades the model's picture into yours just inside its edge. Tone match is fully on, so the new area is adjusted to your picture's tone."
             ],
             "widgets_values_named": {
-              "text": "Blend in fades the model's picture into yours just inside its edge, with no tone shift. The new area stays as painted."
+              "text": "Blend in fades the model's picture into yours just inside its edge. Tone match is fully on, so the new area is adjusted to your picture's tone."
             },
             "color": "#1f2c38",
             "bgcolor": "#2a3b4a"

example_workflows/Qwen Image 2.1 Inpaint (AusBoss).json

@@ -37,10 +37,10 @@
     "Node name for S&R": "AUSBOSS_NODES_WorkflowNote"
    },
    "widgets_values": [
-    "{\"v\": 1, \"title\": \"Qwen Image 2.1 Inpaint\", \"subtitle\": \"Click a thing in your picture and say what to change. Only that part is repainted.\", \"author\": \"AusBoss\", \"layout\": \"card\", \"accent\": \"\", \"body\": \"1. Load your image. You can crop it right there with the blue handles.\\n2. On **Mask by Touch**, click the thing you want to change. It lights up before you click.\\n3. In **What to change**, say it the way you would ask a person: \\\"Replace the cup with a glass of orange juice.\\\"\\n4. Press **Run**.\\n\\nOnly the picked part is repainted. Everything outside it stays your own picture.\\n\\n### Tips\\n- Wrong thing picked? The arrows under the picture swap it for the next thing it could mean.\\n- Name everything that should go: \\\"the iced coffee and its straw\\\". What you do not name can stay.\\n- To remove something, pick it and write \\\"Remove the cup.\\\" Pick its shadow too, or the shadow stays.\\n- To add something, switch to **Paint** and paint where it should go, with some room. Say how big: \\\"Add small black sunglasses on her eyes.\\\"\\n- Not what you wanted? Run it again. The seed changes each run.\\n\\n### Switches\\n- **Fast** on: 8 steps with the Viggle Turbo LoRA from the list below. Off: 25 steps without it, about twice as long.\\n\\nNeeds ComfyUI 0.38 or newer and AusBoss nodes 2.12.0 or newer (update first).\", \"models\": [{\"name\": \"qwen_image_2.1_int8_convrot.safetensors\", \"dir\": \"diffusion_models\", \"size\": \"7.26 GB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/diffusion_models/qwen_image_2.1_int8_convrot.safetensors\", \"note\": \"\"}, {\"name\": \"qwen3vl_8b_int8_convrot.safetensors\", \"dir\": \"text_encoders\", \"size\": \"9.35 GB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/text_encoders/qwen3vl_8b_int8_convrot.safetensors\", \"note\": \"\"}, {\"name\": \"qwen_image_2.1_vae_bf16.safetensors\", \"dir\": \"vae\", \"size\": \"676 MB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/vae/qwen_image_2.1_vae_bf16.safetensors\", \"note\": \"\"}, {\"name\": \"sam3.1_multiplex_fp16.safetensors\", \"dir\": \"checkpoints\", \"size\": \"1.75 GB\", \"url\": \"https://huggingface.co/Comfy-Org/sam3.1/resolve/main/checkpoints/sam3.1_multiplex_fp16.safetensors\", \"note\": \"by Meta, packaged by Comfy-Org\"}, {\"name\": \"Qwen-Image-2.1-viggle-turbo-v0.3-6step-lora-r128.safetensors\", \"dir\": \"loras\", \"size\": \"680 MB\", \"url\": \"https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo/resolve/main/Qwen-Image-2.1-viggle-turbo-v0.3-6step-lora-r128.safetensors\", \"note\": \"optional, for Fast · Qwen Research License, research use\"}], \"packs\": [{\"name\": \"ComfyUI-AusBoss\", \"url\": \"https://github.com/ausboss/ComfyUI-AusBoss\", \"node\": \"AUSBOSS_NODES_MaskByTouch\"}], \"links\": [{\"label\": \"YouTube · this workflow\", \"url\": \"https://youtu.be/iMgaiXoB0v4\"}, {\"label\": \"GitHub · ausboss\", \"url\": \"https://github.com/ausboss\"}, {\"label\": \"Civitai · AusBoss\", \"url\": \"https://civitai.com/user/AusBoss\"}, {\"label\": \"X · Zanzibased\", \"url\": \"https://x.com/Zanzibased\"}]}"
+    "{\"v\": 1, \"title\": \"Qwen Image 2.1 Inpaint\", \"subtitle\": \"Click a thing in your picture and say what to change. Only that part is repainted.\", \"author\": \"AusBoss\", \"layout\": \"card\", \"accent\": \"\", \"body\": \"1. Load your image. You can crop it right there with the blue handles.\\n2. On **Mask by Touch**, click the thing you want to change. It lights up before you click.\\n3. In **What to change**, say it the way you would ask a person: \\\"Replace the cup with a glass of orange juice.\\\"\\n4. Press **Run**.\\n\\nOnly the picked part is repainted. Everything outside it stays your own picture.\\n\\n### Tips\\n- Wrong thing picked? The arrows under the picture swap it for the next thing it could mean.\\n- Name everything that should go: \\\"the iced coffee and its straw\\\". What you do not name can stay.\\n- To remove something, pick it and write \\\"Remove the cup.\\\" Pick its shadow too, or the shadow stays.\\n- To add something, switch to **Paint** and paint where it should go, with some room. Say how big: \\\"Add small black sunglasses on her eyes.\\\"\\n- Not what you wanted? Change **Seed** and run it again. It stays fixed between runs.\\n\\n### Switches\\n- **Fast** on: 8 steps with the Viggle Turbo LoRA from the list below. Off: 25 steps without it, about twice as long.\\n\\nNeeds ComfyUI 0.38 or newer and AusBoss nodes 2.12.0 or newer (update first).\", \"models\": [{\"name\": \"qwen_image_2.1_int8_convrot.safetensors\", \"dir\": \"diffusion_models\", \"size\": \"7.26 GB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/diffusion_models/qwen_image_2.1_int8_convrot.safetensors\", \"note\": \"\"}, {\"name\": \"qwen3vl_8b_int8_convrot.safetensors\", \"dir\": \"text_encoders\", \"size\": \"9.35 GB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/text_encoders/qwen3vl_8b_int8_convrot.safetensors\", \"note\": \"\"}, {\"name\": \"qwen_image_2.1_vae_bf16.safetensors\", \"dir\": \"vae\", \"size\": \"676 MB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/vae/qwen_image_2.1_vae_bf16.safetensors\", \"note\": \"\"}, {\"name\": \"sam3.1_multiplex_fp16.safetensors\", \"dir\": \"checkpoints\", \"size\": \"1.75 GB\", \"url\": \"https://huggingface.co/Comfy-Org/sam3.1/resolve/main/checkpoints/sam3.1_multiplex_fp16.safetensors\", \"note\": \"by Meta, packaged by Comfy-Org\"}, {\"name\": \"Qwen-Image-2.1-viggle-turbo-v0.3-6step-lora-r128.safetensors\", \"dir\": \"loras\", \"size\": \"680 MB\", \"url\": \"https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo/resolve/main/Qwen-Image-2.1-viggle-turbo-v0.3-6step-lora-r128.safetensors\", \"note\": \"optional, for Fast · Qwen Research License, research use\"}], \"packs\": [{\"name\": \"ComfyUI-AusBoss\", \"url\": \"https://github.com/ausboss/ComfyUI-AusBoss\", \"node\": \"AUSBOSS_NODES_MaskByTouch\"}], \"links\": [{\"label\": \"YouTube · this workflow\", \"url\": \"https://youtu.be/iMgaiXoB0v4\"}, {\"label\": \"GitHub · ausboss\", \"url\": \"https://github.com/ausboss\"}, {\"label\": \"Civitai · AusBoss\", \"url\": \"https://civitai.com/user/AusBoss\"}, {\"label\": \"X · Zanzibased\", \"url\": \"https://x.com/Zanzibased\"}]}"
    ],
    "widgets_values_named": {
-    "note": "{\"v\": 1, \"title\": \"Qwen Image 2.1 Inpaint\", \"subtitle\": \"Click a thing in your picture and say what to change. Only that part is repainted.\", \"author\": \"AusBoss\", \"layout\": \"card\", \"accent\": \"\", \"body\": \"1. Load your image. You can crop it right there with the blue handles.\\n2. On **Mask by Touch**, click the thing you want to change. It lights up before you click.\\n3. In **What to change**, say it the way you would ask a person: \\\"Replace the cup with a glass of orange juice.\\\"\\n4. Press **Run**.\\n\\nOnly the picked part is repainted. Everything outside it stays your own picture.\\n\\n### Tips\\n- Wrong thing picked? The arrows under the picture swap it for the next thing it could mean.\\n- Name everything that should go: \\\"the iced coffee and its straw\\\". What you do not name can stay.\\n- To remove something, pick it and write \\\"Remove the cup.\\\" Pick its shadow too, or the shadow stays.\\n- To add something, switch to **Paint** and paint where it should go, with some room. Say how big: \\\"Add small black sunglasses on her eyes.\\\"\\n- Not what you wanted? Run it again. The seed changes each run.\\n\\n### Switches\\n- **Fast** on: 8 steps with the Viggle Turbo LoRA from the list below. Off: 25 steps without it, about twice as long.\\n\\nNeeds ComfyUI 0.38 or newer and AusBoss nodes 2.12.0 or newer (update first).\", \"models\": [{\"name\": \"qwen_image_2.1_int8_convrot.safetensors\", \"dir\": \"diffusion_models\", \"size\": \"7.26 GB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/diffusion_models/qwen_image_2.1_int8_convrot.safetensors\", \"note\": \"\"}, {\"name\": \"qwen3vl_8b_int8_convrot.safetensors\", \"dir\": \"text_encoders\", \"size\": \"9.35 GB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/text_encoders/qwen3vl_8b_int8_convrot.safetensors\", \"note\": \"\"}, {\"name\": \"qwen_image_2.1_vae_bf16.safetensors\", \"dir\": \"vae\", \"size\": \"676 MB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/vae/qwen_image_2.1_vae_bf16.safetensors\", \"note\": \"\"}, {\"name\": \"sam3.1_multiplex_fp16.safetensors\", \"dir\": \"checkpoints\", \"size\": \"1.75 GB\", \"url\": \"https://huggingface.co/Comfy-Org/sam3.1/resolve/main/checkpoints/sam3.1_multiplex_fp16.safetensors\", \"note\": \"by Meta, packaged by Comfy-Org\"}, {\"name\": \"Qwen-Image-2.1-viggle-turbo-v0.3-6step-lora-r128.safetensors\", \"dir\": \"loras\", \"size\": \"680 MB\", \"url\": \"https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo/resolve/main/Qwen-Image-2.1-viggle-turbo-v0.3-6step-lora-r128.safetensors\", \"note\": \"optional, for Fast · Qwen Research License, research use\"}], \"packs\": [{\"name\": \"ComfyUI-AusBoss\", \"url\": \"https://github.com/ausboss/ComfyUI-AusBoss\", \"node\": \"AUSBOSS_NODES_MaskByTouch\"}], \"links\": [{\"label\": \"YouTube · this workflow\", \"url\": \"https://youtu.be/iMgaiXoB0v4\"}, {\"label\": \"GitHub · ausboss\", \"url\": \"https://github.com/ausboss\"}, {\"label\": \"Civitai · AusBoss\", \"url\": \"https://civitai.com/user/AusBoss\"}, {\"label\": \"X · Zanzibased\", \"url\": \"https://x.com/Zanzibased\"}]}"
+    "note": "{\"v\": 1, \"title\": \"Qwen Image 2.1 Inpaint\", \"subtitle\": \"Click a thing in your picture and say what to change. Only that part is repainted.\", \"author\": \"AusBoss\", \"layout\": \"card\", \"accent\": \"\", \"body\": \"1. Load your image. You can crop it right there with the blue handles.\\n2. On **Mask by Touch**, click the thing you want to change. It lights up before you click.\\n3. In **What to change**, say it the way you would ask a person: \\\"Replace the cup with a glass of orange juice.\\\"\\n4. Press **Run**.\\n\\nOnly the picked part is repainted. Everything outside it stays your own picture.\\n\\n### Tips\\n- Wrong thing picked? The arrows under the picture swap it for the next thing it could mean.\\n- Name everything that should go: \\\"the iced coffee and its straw\\\". What you do not name can stay.\\n- To remove something, pick it and write \\\"Remove the cup.\\\" Pick its shadow too, or the shadow stays.\\n- To add something, switch to **Paint** and paint where it should go, with some room. Say how big: \\\"Add small black sunglasses on her eyes.\\\"\\n- Not what you wanted? Change **Seed** and run it again. It stays fixed between runs.\\n\\n### Switches\\n- **Fast** on: 8 steps with the Viggle Turbo LoRA from the list below. Off: 25 steps without it, about twice as long.\\n\\nNeeds ComfyUI 0.38 or newer and AusBoss nodes 2.12.0 or newer (update first).\", \"models\": [{\"name\": \"qwen_image_2.1_int8_convrot.safetensors\", \"dir\": \"diffusion_models\", \"size\": \"7.26 GB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/diffusion_models/qwen_image_2.1_int8_convrot.safetensors\", \"note\": \"\"}, {\"name\": \"qwen3vl_8b_int8_convrot.safetensors\", \"dir\": \"text_encoders\", \"size\": \"9.35 GB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/text_encoders/qwen3vl_8b_int8_convrot.safetensors\", \"note\": \"\"}, {\"name\": \"qwen_image_2.1_vae_bf16.safetensors\", \"dir\": \"vae\", \"size\": \"676 MB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/vae/qwen_image_2.1_vae_bf16.safetensors\", \"note\": \"\"}, {\"name\": \"sam3.1_multiplex_fp16.safetensors\", \"dir\": \"checkpoints\", \"size\": \"1.75 GB\", \"url\": \"https://huggingface.co/Comfy-Org/sam3.1/resolve/main/checkpoints/sam3.1_multiplex_fp16.safetensors\", \"note\": \"by Meta, packaged by Comfy-Org\"}, {\"name\": \"Qwen-Image-2.1-viggle-turbo-v0.3-6step-lora-r128.safetensors\", \"dir\": \"loras\", \"size\": \"680 MB\", \"url\": \"https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo/resolve/main/Qwen-Image-2.1-viggle-turbo-v0.3-6step-lora-r128.safetensors\", \"note\": \"optional, for Fast · Qwen Research License, research use\"}], \"packs\": [{\"name\": \"ComfyUI-AusBoss\", \"url\": \"https://github.com/ausboss/ComfyUI-AusBoss\", \"node\": \"AUSBOSS_NODES_MaskByTouch\"}], \"links\": [{\"label\": \"YouTube · this workflow\", \"url\": \"https://youtu.be/iMgaiXoB0v4\"}, {\"label\": \"GitHub · ausboss\", \"url\": \"https://github.com/ausboss\"}, {\"label\": \"Civitai · AusBoss\", \"url\": \"https://civitai.com/user/AusBoss\"}, {\"label\": \"X · Zanzibased\", \"url\": \"https://x.com/Zanzibased\"}]}"
    },
    "color": "#14424d",
    "bgcolor": "#161f21"

example_workflows/Qwen Image 2.1 Upscale + Restore (AusBoss).json

@@ -37,10 +37,10 @@
     "ver": "2.9.0"
    },
    "widgets_values": [
-    "{\"v\": 1, \"title\": \"Qwen Image 2.1 Upscale + Restore\", \"subtitle\": \"Load a small, soft or worn picture. Qwen Image 2.1 redraws it sharp at the megapixels you set, in its own colors.\", \"author\": \"AusBoss\", \"layout\": \"card\", \"accent\": \"\", \"body\": \"[▶ AusBoss on YouTube](https://www.youtube.com/@ausbossdev) · videos on these nodes and workflows\\n\\n---\\n\\n1. Load your image. You can crop it right there with the blue handles.\\n2. Set **Megapixels**: the size of the result.\\n3. Press **Run**.\\n4. Slide **Before and after** to compare. The result is saved as a PNG.\\n\\n### What you get\\n\\n- Your picture redrawn sharp, at the size you asked for.\\n- Its own colors, also on a noisy or faded photo.\\n\\n### Megapixels\\n\\n- Up to about 2: one pass.\\n- Over that: redrawn in tiles of about 2 megapixels and joined. 4 takes two tiles, 8 takes four.\\n- A small picture is redrawn at up to 8 times its own megapixels, then enlarged the plain way.\\n- A picture of 1 megapixel or more only looks better when it grows about 1.6 times per side.\\n\\n### Switches\\n\\n- **Fast** on: 8 steps with the Viggle Turbo LoRA. Off: 25 steps without it, about three times as long.\\n\\n### Tips\\n\\n- It is a redraw. Fine detail is made up to fit, so a face stays the same person, not the same pixels.\\n- Small lettering on signs and labels can come back misspelled.\\n- Each tile is matched to your picture's colors. To let Qwen's own colors through, lower **Keep colors** inside the box.\\n- If the run stops at a red **LoRA Loader**, a LoRA that is switched on is missing. Download it from the list below.\\n- Not tested on blur from a moving camera or missed focus.\\n\\nNeeds ComfyUI 0.38 or newer and AusBoss nodes 2.9.0 or newer (update first).\", \"models\": [{\"name\": \"qwen_image_2.1_int8_convrot.safetensors\", \"dir\": \"diffusion_models\", \"size\": \"7.26 GB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/diffusion_models/qwen_image_2.1_int8_convrot.safetensors\", \"note\": \"\"}, {\"name\": \"qwen3vl_8b_int8_convrot.safetensors\", \"dir\": \"text_encoders\", \"size\": \"9.35 GB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/text_encoders/qwen3vl_8b_int8_convrot.safetensors\", \"note\": \"\"}, {\"name\": \"qwen_image_2.1_vae_bf16.safetensors\", \"dir\": \"vae\", \"size\": \"676 MB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/vae/qwen_image_2.1_vae_bf16.safetensors\", \"note\": \"\"}, {\"name\": \"qwen-image-2.1-restore.safetensors\", \"dir\": \"loras\", \"size\": \"159 MB\", \"url\": \"https://huggingface.co/ausboss/Qwen-Image-2.1-Restore-LoRA/resolve/main/qwen-image-2.1-restore.safetensors\", \"note\": \"keeps the result close to your picture\"}, {\"name\": \"Qwen-Image-2.1-viggle-turbo-v0.3-6step-lora-r128.safetensors\", \"dir\": \"loras\", \"size\": \"680 MB\", \"url\": \"https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo/resolve/main/Qwen-Image-2.1-viggle-turbo-v0.3-6step-lora-r128.safetensors\", \"note\": \"for Fast on · Qwen Research License, research use\"}], \"packs\": [{\"name\": \"ComfyUI-AusBoss\", \"url\": \"https://github.com/ausboss/ComfyUI-AusBoss\", \"node\": \"AUSBOSS_NODES_TiledUpscale\"}], \"links\": [{\"label\": \"YouTube · ausbossdev\", \"url\": \"https://www.youtube.com/@ausbossdev\"}, {\"label\": \"GitHub · ausboss\", \"url\": \"https://github.com/ausboss\"}, {\"label\": \"Civitai · AusBoss\", \"url\": \"https://civitai.com/user/AusBoss\"}, {\"label\": \"X · Zanzibased\", \"url\": \"https://x.com/Zanzibased\"}]}"
+    "{\"v\": 1, \"title\": \"Qwen Image 2.1 Upscale + Restore\", \"subtitle\": \"Load a small, soft or worn picture. Qwen Image 2.1 redraws it sharp at the megapixels you set, in its own colors.\", \"author\": \"AusBoss\", \"layout\": \"card\", \"accent\": \"\", \"body\": \"[▶ AusBoss on YouTube](https://www.youtube.com/@ausbossdev) · videos on these nodes and workflows\\n\\n---\\n\\n1. Load your image. You can crop it right there with the blue handles.\\n2. Set **Megapixels**: the size of the result.\\n3. Press **Run**.\\n4. Slide **Before and after** to compare. The result is saved as a PNG.\\n\\n### What you get\\n\\n- Your picture redrawn sharp, at the size you asked for.\\n- Its own colors, also on a noisy or faded photo.\\n\\n### Megapixels\\n\\n- Up to about 2: one pass.\\n- Over that: redrawn in tiles of about 2 megapixels and joined. 4 takes two tiles, 8 takes four.\\n- The redraw limit for a small picture is 8 times its own megapixels or one roughly 2 megapixel tile, whichever is larger. The rest is enlarged the plain way.\\n- A picture of 1 megapixel or more only looks better when it grows about 1.6 times per side.\\n\\n### Switches\\n\\n- **Fast** on: 8 steps with the Viggle Turbo LoRA. Off: 25 steps without it, about three times as long.\\n\\n### Tips\\n\\n- It is a redraw. Fine detail is made up to fit, so a face stays the same person, not the same pixels.\\n- Small lettering on signs and labels can come back misspelled.\\n- Each tile is matched to your picture's colors. To let Qwen's own colors through, lower **Keep colors** inside the box.\\n- If the run stops at a red **LoRA Loader**, a LoRA that is switched on is missing. Download it from the list below.\\n- Not tested on blur from a moving camera or missed focus.\\n\\nNeeds ComfyUI 0.38 or newer and AusBoss nodes 2.9.0 or newer (update first).\", \"models\": [{\"name\": \"qwen_image_2.1_int8_convrot.safetensors\", \"dir\": \"diffusion_models\", \"size\": \"7.26 GB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/diffusion_models/qwen_image_2.1_int8_convrot.safetensors\", \"note\": \"\"}, {\"name\": \"qwen3vl_8b_int8_convrot.safetensors\", \"dir\": \"text_encoders\", \"size\": \"9.35 GB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/text_encoders/qwen3vl_8b_int8_convrot.safetensors\", \"note\": \"\"}, {\"name\": \"qwen_image_2.1_vae_bf16.safetensors\", \"dir\": \"vae\", \"size\": \"676 MB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/vae/qwen_image_2.1_vae_bf16.safetensors\", \"note\": \"\"}, {\"name\": \"qwen-image-2.1-restore.safetensors\", \"dir\": \"loras\", \"size\": \"159 MB\", \"url\": \"https://huggingface.co/ausboss/Qwen-Image-2.1-Restore-LoRA/resolve/main/qwen-image-2.1-restore.safetensors\", \"note\": \"keeps the result close to your picture\"}, {\"name\": \"Qwen-Image-2.1-viggle-turbo-v0.3-6step-lora-r128.safetensors\", \"dir\": \"loras\", \"size\": \"680 MB\", \"url\": \"https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo/resolve/main/Qwen-Image-2.1-viggle-turbo-v0.3-6step-lora-r128.safetensors\", \"note\": \"for Fast on · Qwen Research License, research use\"}], \"packs\": [{\"name\": \"ComfyUI-AusBoss\", \"url\": \"https://github.com/ausboss/ComfyUI-AusBoss\", \"node\": \"AUSBOSS_NODES_TiledUpscale\"}], \"links\": [{\"label\": \"YouTube · ausbossdev\", \"url\": \"https://www.youtube.com/@ausbossdev\"}, {\"label\": \"GitHub · ausboss\", \"url\": \"https://github.com/ausboss\"}, {\"label\": \"Civitai · AusBoss\", \"url\": \"https://civitai.com/user/AusBoss\"}, {\"label\": \"X · Zanzibased\", \"url\": \"https://x.com/Zanzibased\"}]}"
    ],
    "widgets_values_named": {
-    "note": "{\"v\": 1, \"title\": \"Qwen Image 2.1 Upscale + Restore\", \"subtitle\": \"Load a small, soft or worn picture. Qwen Image 2.1 redraws it sharp at the megapixels you set, in its own colors.\", \"author\": \"AusBoss\", \"layout\": \"card\", \"accent\": \"\", \"body\": \"[▶ AusBoss on YouTube](https://www.youtube.com/@ausbossdev) · videos on these nodes and workflows\\n\\n---\\n\\n1. Load your image. You can crop it right there with the blue handles.\\n2. Set **Megapixels**: the size of the result.\\n3. Press **Run**.\\n4. Slide **Before and after** to compare. The result is saved as a PNG.\\n\\n### What you get\\n\\n- Your picture redrawn sharp, at the size you asked for.\\n- Its own colors, also on a noisy or faded photo.\\n\\n### Megapixels\\n\\n- Up to about 2: one pass.\\n- Over that: redrawn in tiles of about 2 megapixels and joined. 4 takes two tiles, 8 takes four.\\n- A small picture is redrawn at up to 8 times its own megapixels, then enlarged the plain way.\\n- A picture of 1 megapixel or more only looks better when it grows about 1.6 times per side.\\n\\n### Switches\\n\\n- **Fast** on: 8 steps with the Viggle Turbo LoRA. Off: 25 steps without it, about three times as long.\\n\\n### Tips\\n\\n- It is a redraw. Fine detail is made up to fit, so a face stays the same person, not the same pixels.\\n- Small lettering on signs and labels can come back misspelled.\\n- Each tile is matched to your picture's colors. To let Qwen's own colors through, lower **Keep colors** inside the box.\\n- If the run stops at a red **LoRA Loader**, a LoRA that is switched on is missing. Download it from the list below.\\n- Not tested on blur from a moving camera or missed focus.\\n\\nNeeds ComfyUI 0.38 or newer and AusBoss nodes 2.9.0 or newer (update first).\", \"models\": [{\"name\": \"qwen_image_2.1_int8_convrot.safetensors\", \"dir\": \"diffusion_models\", \"size\": \"7.26 GB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/diffusion_models/qwen_image_2.1_int8_convrot.safetensors\", \"note\": \"\"}, {\"name\": \"qwen3vl_8b_int8_convrot.safetensors\", \"dir\": \"text_encoders\", \"size\": \"9.35 GB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/text_encoders/qwen3vl_8b_int8_convrot.safetensors\", \"note\": \"\"}, {\"name\": \"qwen_image_2.1_vae_bf16.safetensors\", \"dir\": \"vae\", \"size\": \"676 MB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/vae/qwen_image_2.1_vae_bf16.safetensors\", \"note\": \"\"}, {\"name\": \"qwen-image-2.1-restore.safetensors\", \"dir\": \"loras\", \"size\": \"159 MB\", \"url\": \"https://huggingface.co/ausboss/Qwen-Image-2.1-Restore-LoRA/resolve/main/qwen-image-2.1-restore.safetensors\", \"note\": \"keeps the result close to your picture\"}, {\"name\": \"Qwen-Image-2.1-viggle-turbo-v0.3-6step-lora-r128.safetensors\", \"dir\": \"loras\", \"size\": \"680 MB\", \"url\": \"https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo/resolve/main/Qwen-Image-2.1-viggle-turbo-v0.3-6step-lora-r128.safetensors\", \"note\": \"for Fast on · Qwen Research License, research use\"}], \"packs\": [{\"name\": \"ComfyUI-AusBoss\", \"url\": \"https://github.com/ausboss/ComfyUI-AusBoss\", \"node\": \"AUSBOSS_NODES_TiledUpscale\"}], \"links\": [{\"label\": \"YouTube · ausbossdev\", \"url\": \"https://www.youtube.com/@ausbossdev\"}, {\"label\": \"GitHub · ausboss\", \"url\": \"https://github.com/ausboss\"}, {\"label\": \"Civitai · AusBoss\", \"url\": \"https://civitai.com/user/AusBoss\"}, {\"label\": \"X · Zanzibased\", \"url\": \"https://x.com/Zanzibased\"}]}"
+    "note": "{\"v\": 1, \"title\": \"Qwen Image 2.1 Upscale + Restore\", \"subtitle\": \"Load a small, soft or worn picture. Qwen Image 2.1 redraws it sharp at the megapixels you set, in its own colors.\", \"author\": \"AusBoss\", \"layout\": \"card\", \"accent\": \"\", \"body\": \"[▶ AusBoss on YouTube](https://www.youtube.com/@ausbossdev) · videos on these nodes and workflows\\n\\n---\\n\\n1. Load your image. You can crop it right there with the blue handles.\\n2. Set **Megapixels**: the size of the result.\\n3. Press **Run**.\\n4. Slide **Before and after** to compare. The result is saved as a PNG.\\n\\n### What you get\\n\\n- Your picture redrawn sharp, at the size you asked for.\\n- Its own colors, also on a noisy or faded photo.\\n\\n### Megapixels\\n\\n- Up to about 2: one pass.\\n- Over that: redrawn in tiles of about 2 megapixels and joined. 4 takes two tiles, 8 takes four.\\n- The redraw limit for a small picture is 8 times its own megapixels or one roughly 2 megapixel tile, whichever is larger. The rest is enlarged the plain way.\\n- A picture of 1 megapixel or more only looks better when it grows about 1.6 times per side.\\n\\n### Switches\\n\\n- **Fast** on: 8 steps with the Viggle Turbo LoRA. Off: 25 steps without it, about three times as long.\\n\\n### Tips\\n\\n- It is a redraw. Fine detail is made up to fit, so a face stays the same person, not the same pixels.\\n- Small lettering on signs and labels can come back misspelled.\\n- Each tile is matched to your picture's colors. To let Qwen's own colors through, lower **Keep colors** inside the box.\\n- If the run stops at a red **LoRA Loader**, a LoRA that is switched on is missing. Download it from the list below.\\n- Not tested on blur from a moving camera or missed focus.\\n\\nNeeds ComfyUI 0.38 or newer and AusBoss nodes 2.9.0 or newer (update first).\", \"models\": [{\"name\": \"qwen_image_2.1_int8_convrot.safetensors\", \"dir\": \"diffusion_models\", \"size\": \"7.26 GB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/diffusion_models/qwen_image_2.1_int8_convrot.safetensors\", \"note\": \"\"}, {\"name\": \"qwen3vl_8b_int8_convrot.safetensors\", \"dir\": \"text_encoders\", \"size\": \"9.35 GB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/text_encoders/qwen3vl_8b_int8_convrot.safetensors\", \"note\": \"\"}, {\"name\": \"qwen_image_2.1_vae_bf16.safetensors\", \"dir\": \"vae\", \"size\": \"676 MB\", \"url\": \"https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/vae/qwen_image_2.1_vae_bf16.safetensors\", \"note\": \"\"}, {\"name\": \"qwen-image-2.1-restore.safetensors\", \"dir\": \"loras\", \"size\": \"159 MB\", \"url\": \"https://huggingface.co/ausboss/Qwen-Image-2.1-Restore-LoRA/resolve/main/qwen-image-2.1-restore.safetensors\", \"note\": \"keeps the result close to your picture\"}, {\"name\": \"Qwen-Image-2.1-viggle-turbo-v0.3-6step-lora-r128.safetensors\", \"dir\": \"loras\", \"size\": \"680 MB\", \"url\": \"https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo/resolve/main/Qwen-Image-2.1-viggle-turbo-v0.3-6step-lora-r128.safetensors\", \"note\": \"for Fast on · Qwen Research License, research use\"}], \"packs\": [{\"name\": \"ComfyUI-AusBoss\", \"url\": \"https://github.com/ausboss/ComfyUI-AusBoss\", \"node\": \"AUSBOSS_NODES_TiledUpscale\"}], \"links\": [{\"label\": \"YouTube · ausbossdev\", \"url\": \"https://www.youtube.com/@ausbossdev\"}, {\"label\": \"GitHub · ausboss\", \"url\": \"https://github.com/ausboss\"}, {\"label\": \"Civitai · AusBoss\", \"url\": \"https://civitai.com/user/AusBoss\"}, {\"label\": \"X · Zanzibased\", \"url\": \"https://x.com/Zanzibased\"}]}"
    },
    "color": "#14424d",
    "bgcolor": "#161f21"