philz1337x / multidiffusion-upscaler
High resolution image Upscaler and Enhancer. Twitter/X: @philz1337x
- Public
- 19.3K runs
-
L40S
- Paper
Prediction
philz1337x/multidiffusion-upscaler:88f19697c15c8befccd557649fe6b01fcfa55ade961c2d1c3c23d9c986fdaff7IDowj767tblz32gyosrwrsnxc74yStatusSucceededSourceWebHardwareA40Total durationCreatedInput
- seed
- 1337
- width
- 512
- height
- 512
- prompt
- masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>
- sd_vae
- vae-ft-mse-840000-ema-pruned.safetensors
- cn_model
- control_v11f1e_sd15_tile
- sd_model
- juggernaut_reborn.safetensors [338b85bc4f]
- cn_module
- tile_resample
- cn_weight
- 0.6
- scheduler
- DPM++ 3M SDE Karras
- td_method
- MultiDiffusion
- cn_lowvram
- td_overlap
- 4
- num_outputs
- 1
- cn_downsample
- 1
- td_tile_width
- 112
- cn_resize_mode
- 1
- cn_threshold_a
- 1
- cn_threshold_b
- 1
- guidance_scale
- 6
- td_image_width
- 1
- td_tile_height
- 144
- cn_control_mode
- 1
- cn_guidance_end
- 1
- negative_prompt
- (worst quality, low quality, normal quality:2) JuggernautNegative-neg
- td_image_height
- 1
- td_scale_factor
- 2
- tv_fast_decoder
- tv_fast_encoder
- cn_pixel_perfect
- enable_tiled_vae
- td_noise_inverse
- td_upscaler_name
- 4x-UltraSharp
- cn_guidance_start
- 0
- enable_controlnet
- td_overwrite_size
- denoising_strength
- 0.35
- td_keep_input_size
- td_tile_batch_size
- 8
- tv_move_vae_to_gpu
- cn_preprocessor_res
- 512
- num_inference_steps
- 18
- tv_decoder_tile_size
- 192
- tv_encoder_tile_size
- 3072
- enable_tiled_diffusion
- td_noise_inverse_steps
- 0
- clip_stop_at_last_layers
- 1
- tv_fast_encoder_color_fix
- td_noise_inverse_renoise_kernel
- 3
- td_noise_inverse_renoise_strength
- 0
{ "seed": 1337, "image": "https://replicate.delivery/pbxt/KZWaur3VOX61FKuhgCYsMUA7oJDI1tCVyGlTWEV3BIqLZOTe/2024-01-02%2009.18.49.jpg", "width": 512, "height": 512, "prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>", "sd_vae": "vae-ft-mse-840000-ema-pruned.safetensors", "cn_model": "control_v11f1e_sd15_tile", "sd_model": "juggernaut_reborn.safetensors [338b85bc4f]", "cn_module": "tile_resample", "cn_weight": 0.6, "scheduler": "DPM++ 3M SDE Karras", "td_method": "MultiDiffusion", "cn_lowvram": false, "td_overlap": 4, "num_outputs": 1, "cn_downsample": 1, "td_tile_width": 112, "cn_resize_mode": 1, "cn_threshold_a": 1, "cn_threshold_b": 1, "guidance_scale": 6, "td_image_width": 1, "td_tile_height": 144, "cn_control_mode": 1, "cn_guidance_end": 1, "negative_prompt": "(worst quality, low quality, normal quality:2) JuggernautNegative-neg", "td_image_height": 1, "td_scale_factor": 2, "tv_fast_decoder": true, "tv_fast_encoder": true, "cn_pixel_perfect": true, "enable_tiled_vae": true, "td_noise_inverse": false, "td_upscaler_name": "4x-UltraSharp", "cn_guidance_start": 0, "enable_controlnet": true, "td_overwrite_size": true, "denoising_strength": 0.35, "td_keep_input_size": true, "td_tile_batch_size": 8, "tv_move_vae_to_gpu": true, "cn_preprocessor_res": 512, "num_inference_steps": 18, "tv_decoder_tile_size": 192, "tv_encoder_tile_size": 3072, "enable_tiled_diffusion": true, "td_noise_inverse_steps": 0, "clip_stop_at_last_layers": 1, "tv_fast_encoder_color_fix": true, "td_noise_inverse_renoise_kernel": 3, "td_noise_inverse_renoise_strength": 0 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run philz1337x/multidiffusion-upscaler using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "philz1337x/multidiffusion-upscaler:88f19697c15c8befccd557649fe6b01fcfa55ade961c2d1c3c23d9c986fdaff7", { input: { seed: 1337, image: "https://replicate.delivery/pbxt/KZWaur3VOX61FKuhgCYsMUA7oJDI1tCVyGlTWEV3BIqLZOTe/2024-01-02%2009.18.49.jpg", width: 512, height: 512, prompt: "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>", sd_vae: "vae-ft-mse-840000-ema-pruned.safetensors", cn_model: "control_v11f1e_sd15_tile", sd_model: "juggernaut_reborn.safetensors [338b85bc4f]", cn_module: "tile_resample", cn_weight: 0.6, scheduler: "DPM++ 3M SDE Karras", td_method: "MultiDiffusion", cn_lowvram: false, td_overlap: 4, num_outputs: 1, cn_downsample: 1, td_tile_width: 112, cn_resize_mode: 1, cn_threshold_a: 1, cn_threshold_b: 1, guidance_scale: 6, td_image_width: 1, td_tile_height: 144, cn_control_mode: 1, cn_guidance_end: 1, negative_prompt: "(worst quality, low quality, normal quality:2) JuggernautNegative-neg", td_image_height: 1, td_scale_factor: 2, tv_fast_decoder: true, tv_fast_encoder: true, cn_pixel_perfect: true, enable_tiled_vae: true, td_noise_inverse: false, td_upscaler_name: "4x-UltraSharp", cn_guidance_start: 0, enable_controlnet: true, td_overwrite_size: true, denoising_strength: 0.35, td_keep_input_size: true, td_tile_batch_size: 8, tv_move_vae_to_gpu: true, cn_preprocessor_res: 512, num_inference_steps: 18, tv_decoder_tile_size: 192, tv_encoder_tile_size: 3072, enable_tiled_diffusion: true, td_noise_inverse_steps: 0, clip_stop_at_last_layers: 1, tv_fast_encoder_color_fix: true, td_noise_inverse_renoise_kernel: 3, td_noise_inverse_renoise_strength: 0 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run philz1337x/multidiffusion-upscaler using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "philz1337x/multidiffusion-upscaler:88f19697c15c8befccd557649fe6b01fcfa55ade961c2d1c3c23d9c986fdaff7", input={ "seed": 1337, "image": "https://replicate.delivery/pbxt/KZWaur3VOX61FKuhgCYsMUA7oJDI1tCVyGlTWEV3BIqLZOTe/2024-01-02%2009.18.49.jpg", "width": 512, "height": 512, "prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>", "sd_vae": "vae-ft-mse-840000-ema-pruned.safetensors", "cn_model": "control_v11f1e_sd15_tile", "sd_model": "juggernaut_reborn.safetensors [338b85bc4f]", "cn_module": "tile_resample", "cn_weight": 0.6, "scheduler": "DPM++ 3M SDE Karras", "td_method": "MultiDiffusion", "cn_lowvram": False, "td_overlap": 4, "num_outputs": 1, "cn_downsample": 1, "td_tile_width": 112, "cn_resize_mode": 1, "cn_threshold_a": 1, "cn_threshold_b": 1, "guidance_scale": 6, "td_image_width": 1, "td_tile_height": 144, "cn_control_mode": 1, "cn_guidance_end": 1, "negative_prompt": "(worst quality, low quality, normal quality:2) JuggernautNegative-neg", "td_image_height": 1, "td_scale_factor": 2, "tv_fast_decoder": True, "tv_fast_encoder": True, "cn_pixel_perfect": True, "enable_tiled_vae": True, "td_noise_inverse": False, "td_upscaler_name": "4x-UltraSharp", "cn_guidance_start": 0, "enable_controlnet": True, "td_overwrite_size": True, "denoising_strength": 0.35, "td_keep_input_size": True, "td_tile_batch_size": 8, "tv_move_vae_to_gpu": True, "cn_preprocessor_res": 512, "num_inference_steps": 18, "tv_decoder_tile_size": 192, "tv_encoder_tile_size": 3072, "enable_tiled_diffusion": True, "td_noise_inverse_steps": 0, "clip_stop_at_last_layers": 1, "tv_fast_encoder_color_fix": True, "td_noise_inverse_renoise_kernel": 3, "td_noise_inverse_renoise_strength": 0 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run philz1337x/multidiffusion-upscaler using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "philz1337x/multidiffusion-upscaler:88f19697c15c8befccd557649fe6b01fcfa55ade961c2d1c3c23d9c986fdaff7", "input": { "seed": 1337, "image": "https://replicate.delivery/pbxt/KZWaur3VOX61FKuhgCYsMUA7oJDI1tCVyGlTWEV3BIqLZOTe/2024-01-02%2009.18.49.jpg", "width": 512, "height": 512, "prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>", "sd_vae": "vae-ft-mse-840000-ema-pruned.safetensors", "cn_model": "control_v11f1e_sd15_tile", "sd_model": "juggernaut_reborn.safetensors [338b85bc4f]", "cn_module": "tile_resample", "cn_weight": 0.6, "scheduler": "DPM++ 3M SDE Karras", "td_method": "MultiDiffusion", "cn_lowvram": false, "td_overlap": 4, "num_outputs": 1, "cn_downsample": 1, "td_tile_width": 112, "cn_resize_mode": 1, "cn_threshold_a": 1, "cn_threshold_b": 1, "guidance_scale": 6, "td_image_width": 1, "td_tile_height": 144, "cn_control_mode": 1, "cn_guidance_end": 1, "negative_prompt": "(worst quality, low quality, normal quality:2) JuggernautNegative-neg", "td_image_height": 1, "td_scale_factor": 2, "tv_fast_decoder": true, "tv_fast_encoder": true, "cn_pixel_perfect": true, "enable_tiled_vae": true, "td_noise_inverse": false, "td_upscaler_name": "4x-UltraSharp", "cn_guidance_start": 0, "enable_controlnet": true, "td_overwrite_size": true, "denoising_strength": 0.35, "td_keep_input_size": true, "td_tile_batch_size": 8, "tv_move_vae_to_gpu": true, "cn_preprocessor_res": 512, "num_inference_steps": 18, "tv_decoder_tile_size": 192, "tv_encoder_tile_size": 3072, "enable_tiled_diffusion": true, "td_noise_inverse_steps": 0, "clip_stop_at_last_layers": 1, "tv_fast_encoder_color_fix": true, "td_noise_inverse_renoise_kernel": 3, "td_noise_inverse_renoise_strength": 0 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-03-15T04:22:53.518849Z", "created_at": "2024-03-15T04:13:38.557264Z", "data_removed": false, "error": null, "id": "owj767tblz32gyosrwrsnxc74y", "input": { "seed": 1337, "image": "https://replicate.delivery/pbxt/KZWaur3VOX61FKuhgCYsMUA7oJDI1tCVyGlTWEV3BIqLZOTe/2024-01-02%2009.18.49.jpg", "width": 512, "height": 512, "prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>", "sd_vae": "vae-ft-mse-840000-ema-pruned.safetensors", "cn_model": "control_v11f1e_sd15_tile", "sd_model": "juggernaut_reborn.safetensors [338b85bc4f]", "cn_module": "tile_resample", "cn_weight": 0.6, "scheduler": "DPM++ 3M SDE Karras", "td_method": "MultiDiffusion", "cn_lowvram": false, "td_overlap": 4, "num_outputs": 1, "cn_downsample": 1, "td_tile_width": 112, "cn_resize_mode": 1, "cn_threshold_a": 1, "cn_threshold_b": 1, "guidance_scale": 6, "td_image_width": 1, "td_tile_height": 144, "cn_control_mode": 1, "cn_guidance_end": 1, "negative_prompt": "(worst quality, low quality, normal quality:2) JuggernautNegative-neg", "td_image_height": 1, "td_scale_factor": 2, "tv_fast_decoder": true, "tv_fast_encoder": true, "cn_pixel_perfect": true, "enable_tiled_vae": true, "td_noise_inverse": false, "td_upscaler_name": "4x-UltraSharp", "cn_guidance_start": 0, "enable_controlnet": true, "td_overwrite_size": true, "denoising_strength": 0.35, "td_keep_input_size": true, "td_tile_batch_size": 8, "tv_move_vae_to_gpu": true, "cn_preprocessor_res": 512, "num_inference_steps": 18, "tv_decoder_tile_size": 192, "tv_encoder_tile_size": 3072, "enable_tiled_diffusion": true, "td_noise_inverse_steps": 0, "clip_stop_at_last_layers": 1, "tv_fast_encoder_color_fix": true, "td_noise_inverse_renoise_kernel": 3, "td_noise_inverse_renoise_strength": 0 }, "logs": "Creating model from config: /src/configs/v1-inference.yaml\n2024-03-15 04:21:06,285 - ControlNet - \u001b[0;32mINFO\u001b[0m - ControlNet UI callback registered.\nfatal: not a git repository (or any of the parent directories): .git\nfatal: not a git repository (or any of the parent directories): .git\nCouldn't find VAE named None; using None instead\nApplying attention optimization: Doggettx... done.\nModel loaded in 3.8s (load weights from disk: 0.1s, create model: 3.0s, apply weights to model: 0.4s).\nLoading VAE weights specified in settings: /src/models/VAE/vae-ft-mse-840000-ema-pruned.safetensors\nApplying attention optimization: Doggettx... done.\nVAE weights loaded.\n[Tiled Diffusion] upscaling image with 4x-UltraSharp...\n[Tiled Diffusion] ControlNet found, support is enabled.\n2024-03-15 04:21:18,999 - ControlNet - \u001b[0;32mINFO\u001b[0m - unit_separate = False, style_align = False\n2024-03-15 04:21:19,257 - ControlNet - \u001b[0;32mINFO\u001b[0m - Loading model: control_v11f1e_sd15_tile [a371b31b]\n2024-03-15 04:21:19,578 - ControlNet - \u001b[0;32mINFO\u001b[0m - Loaded state_dict from [/src/extensions/sd-webui-controlnet/models/control_v11f1e_sd15_tile.pth]\n2024-03-15 04:21:19,578 - ControlNet - \u001b[0;32mINFO\u001b[0m - controlnet_default_config\n2024-03-15 04:21:21,770 - ControlNet - \u001b[0;32mINFO\u001b[0m - ControlNet model control_v11f1e_sd15_tile [a371b31b](ControlModelType.ControlNet) loaded.\n2024-03-15 04:21:21,815 - ControlNet - \u001b[0;32mINFO\u001b[0m - Using preprocessor: tile_resample\n2024-03-15 04:21:21,815 - ControlNet - \u001b[0;32mINFO\u001b[0m - preprocessor resolution = 2288\n2024-03-15 04:21:22,036 - ControlNet - \u001b[0;32mINFO\u001b[0m - ControlNet Hooked - Time = 3.041232109069824\nMultiDiffusion hooked into 'DPM++ 3M SDE Karras' sampler, Tile size: 144x112, Tile count: 15, Batch size: 8, Tile batches: 2 (ext: ContrlNet)\n[Tiled VAE]: input_size: torch.Size([1, 3, 2288, 4096]), tile_size: 3072, padding: 32\n[Tiled VAE]: split to 1x2 = 2 tiles. Optimal tile size 2016x2240, original tile size 3072x3072\n[Tiled VAE]: Fast mode enabled, estimating group norm parameters on 3072 x 1716 image\nMultiDiffusion Sampling: : 0it [00:00, ?it/s]\n[Tiled VAE]: Executing Encoder Task Queue: 0%| | 0/182 [00:00<?, ?it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 10%|▉ | 18/182 [00:00<00:02, 77.37it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 14%|█▍ | 26/182 [00:00<00:03, 40.82it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 21%|██ | 38/182 [00:01<00:04, 33.10it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 23%|██▎ | 42/182 [00:01<00:05, 26.67it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 26%|██▋ | 48/182 [00:01<00:04, 29.20it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 29%|██▊ | 52/182 [00:01<00:06, 18.73it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 30%|███ | 55/182 [00:02<00:08, 15.39it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 32%|███▏ | 58/182 [00:02<00:09, 13.26it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 35%|███▌ | 64/182 [00:02<00:06, 17.21it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 37%|███▋ | 67/182 [00:03<00:07, 16.21it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 38%|███▊ | 70/182 [00:03<00:06, 17.51it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 40%|████ | 73/182 [00:03<00:05, 18.54it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 42%|████▏ | 76/182 [00:03<00:05, 18.91it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 46%|████▌ | 83/182 [00:03<00:04, 24.54it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 47%|████▋ | 86/182 [00:03<00:04, 23.38it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 49%|████▉ | 89/182 [00:03<00:04, 21.17it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 51%|█████ | 92/182 [00:04<00:04, 20.03it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 54%|█████▍ | 99/182 [00:04<00:02, 29.67it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 57%|█████▋ | 104/182 [00:04<00:02, 30.93it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 65%|██████▍ | 118/182 [00:04<00:01, 53.13it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 74%|███████▎ | 134/182 [00:04<00:00, 76.76it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 82%|████████▏ | 150/182 [00:04<00:00, 95.56it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 88%|████████▊ | 161/182 [00:05<00:00, 41.01it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 97%|█████████▋| 176/182 [00:05<00:00, 54.86it/s]\u001b[A\n[Tiled VAE]: Executing Encoder Task Queue: 100%|██████████| 182/182 [00:05<00:00, 32.97it/s]\n[Tiled VAE]: Done in 6.285s, max VRAM alloc 23998.532 MB\n 0%| | 0/7 [00:00<?, ?it/s]\u001b[A\nMultiDiffusion Sampling: : 0it [00:13, ?it/s]\nTotal progress: 0%| | 0/7 [00:00<?, ?it/s]\u001b[A\n 14%|█▍ | 1/7 [00:11<01:11, 11.99s/it]\u001b[A\nTotal progress: 29%|██▊ | 2/7 [00:10<00:26, 5.25s/it]\u001b[A\n 29%|██▊ | 2/7 [00:22<00:55, 11.12s/it]\u001b[A\nTotal progress: 43%|████▎ | 3/7 [00:21<00:29, 7.44s/it]\u001b[A\n 43%|████▎ | 3/7 [00:33<00:43, 10.84s/it]\u001b[A\nTotal progress: 57%|█████▋ | 4/7 [00:31<00:25, 8.59s/it]\u001b[A\n 57%|█████▋ | 4/7 [00:43<00:32, 10.71s/it]\u001b[A\nTotal progress: 71%|███████▏ | 5/7 [00:42<00:18, 9.26s/it]\u001b[A\n 71%|███████▏ | 5/7 [00:54<00:21, 10.64s/it]\u001b[A\nTotal progress: 86%|████████▌ | 6/7 [00:52<00:09, 9.68s/it]\u001b[A\n 86%|████████▌ | 6/7 [01:04<00:10, 10.60s/it]\u001b[A\n100%|██████████| 7/7 [01:15<00:00, 10.57s/it]\u001b[A\n100%|██████████| 7/7 [01:15<00:00, 10.73s/it]\nTotal progress: 100%|██████████| 7/7 [01:03<00:00, 9.95s/it]\u001b[A[Tiled VAE]: input_size: torch.Size([1, 4, 286, 512]), tile_size: 192, padding: 11\n[Tiled VAE]: split to 2x3 = 6 tiles. Optimal tile size 192x160, original tile size 192x192\n[Tiled VAE]: Fast mode enabled, estimating group norm parameters on 192 x 107 image\n[Tiled VAE]: Executing Decoder Task Queue: 0%| | 0/738 [00:00<?, ?it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 17%|█▋ | 124/738 [00:00<00:02, 210.24it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 33%|███▎ | 247/738 [00:01<00:02, 211.90it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 50%|█████ | 370/738 [00:01<00:01, 263.89it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 67%|██████▋ | 493/738 [00:01<00:00, 282.74it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 83%|████████▎ | 616/738 [00:02<00:00, 294.08it/s]\n[Tiled VAE]: Executing Decoder Task Queue: 100%|██████████| 738/738 [00:02<00:00, 295.40it/s]\n[Tiled VAE]: Done in 3.381s, max VRAM alloc 9362.373 MB\nTotal progress: 100%|██████████| 7/7 [01:07<00:00, 9.95s/it]\u001b[A\nTotal progress: 100%|██████████| 7/7 [01:07<00:00, 9.57s/it]", "metrics": { "predict_time": 108.381481, "total_time": 554.961585 }, "output": [ "https://replicate.delivery/pbxt/5qurYymD5B6VHVZ6k2k9IrvF8t2uq6elfFQno8I9mmTb8XgSA/1337-aff3b668-e283-11ee-9be1-72886dc2033f.png" ], "started_at": "2024-03-15T04:21:05.137368Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/owj767tblz32gyosrwrsnxc74y", "cancel": "https://api.replicate.com/v1/predictions/owj767tblz32gyosrwrsnxc74y/cancel" }, "version": "88f19697c15c8befccd557649fe6b01fcfa55ade961c2d1c3c23d9c986fdaff7" }
Generated inCreating model from config: /src/configs/v1-inference.yaml 2024-03-15 04:21:06,285 - ControlNet - INFO - ControlNet UI callback registered. fatal: not a git repository (or any of the parent directories): .git fatal: not a git repository (or any of the parent directories): .git Couldn't find VAE named None; using None instead Applying attention optimization: Doggettx... done. Model loaded in 3.8s (load weights from disk: 0.1s, create model: 3.0s, apply weights to model: 0.4s). Loading VAE weights specified in settings: /src/models/VAE/vae-ft-mse-840000-ema-pruned.safetensors Applying attention optimization: Doggettx... done. VAE weights loaded. [Tiled Diffusion] upscaling image with 4x-UltraSharp... [Tiled Diffusion] ControlNet found, support is enabled. 2024-03-15 04:21:18,999 - ControlNet - INFO - unit_separate = False, style_align = False 2024-03-15 04:21:19,257 - ControlNet - INFO - Loading model: control_v11f1e_sd15_tile [a371b31b] 2024-03-15 04:21:19,578 - ControlNet - INFO - Loaded state_dict from [/src/extensions/sd-webui-controlnet/models/control_v11f1e_sd15_tile.pth] 2024-03-15 04:21:19,578 - ControlNet - INFO - controlnet_default_config 2024-03-15 04:21:21,770 - ControlNet - INFO - ControlNet model control_v11f1e_sd15_tile [a371b31b](ControlModelType.ControlNet) loaded. 2024-03-15 04:21:21,815 - ControlNet - INFO - Using preprocessor: tile_resample 2024-03-15 04:21:21,815 - ControlNet - INFO - preprocessor resolution = 2288 2024-03-15 04:21:22,036 - ControlNet - INFO - ControlNet Hooked - Time = 3.041232109069824 MultiDiffusion hooked into 'DPM++ 3M SDE Karras' sampler, Tile size: 144x112, Tile count: 15, Batch size: 8, Tile batches: 2 (ext: ContrlNet) [Tiled VAE]: input_size: torch.Size([1, 3, 2288, 4096]), tile_size: 3072, padding: 32 [Tiled VAE]: split to 1x2 = 2 tiles. Optimal tile size 2016x2240, original tile size 3072x3072 [Tiled VAE]: Fast mode enabled, estimating group norm parameters on 3072 x 1716 image MultiDiffusion Sampling: : 0it [00:00, ?it/s] [Tiled VAE]: Executing Encoder Task Queue: 0%| | 0/182 [00:00<?, ?it/s] [Tiled VAE]: Executing Encoder Task Queue: 10%|▉ | 18/182 [00:00<00:02, 77.37it/s] [Tiled VAE]: Executing Encoder Task Queue: 14%|█▍ | 26/182 [00:00<00:03, 40.82it/s] [Tiled VAE]: Executing Encoder Task Queue: 21%|██ | 38/182 [00:01<00:04, 33.10it/s] [Tiled VAE]: Executing Encoder Task Queue: 23%|██▎ | 42/182 [00:01<00:05, 26.67it/s] [Tiled VAE]: Executing Encoder Task Queue: 26%|██▋ | 48/182 [00:01<00:04, 29.20it/s] [Tiled VAE]: Executing Encoder Task Queue: 29%|██▊ | 52/182 [00:01<00:06, 18.73it/s] [Tiled VAE]: Executing Encoder Task Queue: 30%|███ | 55/182 [00:02<00:08, 15.39it/s] [Tiled VAE]: Executing Encoder Task Queue: 32%|███▏ | 58/182 [00:02<00:09, 13.26it/s] [Tiled VAE]: Executing Encoder Task Queue: 35%|███▌ | 64/182 [00:02<00:06, 17.21it/s] [Tiled VAE]: Executing Encoder Task Queue: 37%|███▋ | 67/182 [00:03<00:07, 16.21it/s] [Tiled VAE]: Executing Encoder Task Queue: 38%|███▊ | 70/182 [00:03<00:06, 17.51it/s] [Tiled VAE]: Executing Encoder Task Queue: 40%|████ | 73/182 [00:03<00:05, 18.54it/s] [Tiled VAE]: Executing Encoder Task Queue: 42%|████▏ | 76/182 [00:03<00:05, 18.91it/s] [Tiled VAE]: Executing Encoder Task Queue: 46%|████▌ | 83/182 [00:03<00:04, 24.54it/s] [Tiled VAE]: Executing Encoder Task Queue: 47%|████▋ | 86/182 [00:03<00:04, 23.38it/s] [Tiled VAE]: Executing Encoder Task Queue: 49%|████▉ | 89/182 [00:03<00:04, 21.17it/s] [Tiled VAE]: Executing Encoder Task Queue: 51%|█████ | 92/182 [00:04<00:04, 20.03it/s] [Tiled VAE]: Executing Encoder Task Queue: 54%|█████▍ | 99/182 [00:04<00:02, 29.67it/s] [Tiled VAE]: Executing Encoder Task Queue: 57%|█████▋ | 104/182 [00:04<00:02, 30.93it/s] [Tiled VAE]: Executing Encoder Task Queue: 65%|██████▍ | 118/182 [00:04<00:01, 53.13it/s] [Tiled VAE]: Executing Encoder Task Queue: 74%|███████▎ | 134/182 [00:04<00:00, 76.76it/s] [Tiled VAE]: Executing Encoder Task Queue: 82%|████████▏ | 150/182 [00:04<00:00, 95.56it/s] [Tiled VAE]: Executing Encoder Task Queue: 88%|████████▊ | 161/182 [00:05<00:00, 41.01it/s] [Tiled VAE]: Executing Encoder Task Queue: 97%|█████████▋| 176/182 [00:05<00:00, 54.86it/s] [Tiled VAE]: Executing Encoder Task Queue: 100%|██████████| 182/182 [00:05<00:00, 32.97it/s] [Tiled VAE]: Done in 6.285s, max VRAM alloc 23998.532 MB 0%| | 0/7 [00:00<?, ?it/s] MultiDiffusion Sampling: : 0it [00:13, ?it/s] Total progress: 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:11<01:11, 11.99s/it] Total progress: 29%|██▊ | 2/7 [00:10<00:26, 5.25s/it] 29%|██▊ | 2/7 [00:22<00:55, 11.12s/it] Total progress: 43%|████▎ | 3/7 [00:21<00:29, 7.44s/it] 43%|████▎ | 3/7 [00:33<00:43, 10.84s/it] Total progress: 57%|█████▋ | 4/7 [00:31<00:25, 8.59s/it] 57%|█████▋ | 4/7 [00:43<00:32, 10.71s/it] Total progress: 71%|███████▏ | 5/7 [00:42<00:18, 9.26s/it] 71%|███████▏ | 5/7 [00:54<00:21, 10.64s/it] Total progress: 86%|████████▌ | 6/7 [00:52<00:09, 9.68s/it] 86%|████████▌ | 6/7 [01:04<00:10, 10.60s/it] 100%|██████████| 7/7 [01:15<00:00, 10.57s/it] 100%|██████████| 7/7 [01:15<00:00, 10.73s/it] Total progress: 100%|██████████| 7/7 [01:03<00:00, 9.95s/it][Tiled VAE]: input_size: torch.Size([1, 4, 286, 512]), tile_size: 192, padding: 11 [Tiled VAE]: split to 2x3 = 6 tiles. Optimal tile size 192x160, original tile size 192x192 [Tiled VAE]: Fast mode enabled, estimating group norm parameters on 192 x 107 image [Tiled VAE]: Executing Decoder Task Queue: 0%| | 0/738 [00:00<?, ?it/s] [Tiled VAE]: Executing Decoder Task Queue: 17%|█▋ | 124/738 [00:00<00:02, 210.24it/s] [Tiled VAE]: Executing Decoder Task Queue: 33%|███▎ | 247/738 [00:01<00:02, 211.90it/s] [Tiled VAE]: Executing Decoder Task Queue: 50%|█████ | 370/738 [00:01<00:01, 263.89it/s] [Tiled VAE]: Executing Decoder Task Queue: 67%|██████▋ | 493/738 [00:01<00:00, 282.74it/s] [Tiled VAE]: Executing Decoder Task Queue: 83%|████████▎ | 616/738 [00:02<00:00, 294.08it/s] [Tiled VAE]: Executing Decoder Task Queue: 100%|██████████| 738/738 [00:02<00:00, 295.40it/s] [Tiled VAE]: Done in 3.381s, max VRAM alloc 9362.373 MB Total progress: 100%|██████████| 7/7 [01:07<00:00, 9.95s/it] Total progress: 100%|██████████| 7/7 [01:07<00:00, 9.57s/it]
Want to make some of these yourself?
Run this model