tungsten-logo
Sign In
Darkvred
protovision-xl:r0.6.2.0-base-v4.3
brentlynch
brentlynch
·
Mar 6
334
Input
prompt
Specify things to see in the output
RAW Photography, breathtaking cinematic film still of Maximillian, a giant deadly RED robot with a SINGLE bright glowing RED LED EYE from The Black Hole, terrifying, imposing, whirring blades for hands, evil red eye beam glow, spaceship in background, professional, award-winning, highly detailed, realistic, intricate details, 8k, masterpiece, dynamic play of light, 35mm photograph, kodachrome, dust particles caught in the light, raytracing, RTX, 8K, 4K, HDRI, UHD, extremely detailed, intricately detailed, studio quality, film quality, perfect lighting, perfect shadows, perfect textures, antialiasing, volumetric fog, detailed background, holding gun, photorealistic, lifelike
negative_prompt
Specify things to not see in the output
low quality, low resolution, low detail, out of focus, smudged, smeared, unrefined, unfinished, blurry, pixelated, artifacts, compression, JPEG
num_outputs
Number of output images
3
width
Output image width
1024
height
Output image height
1024
enhance_face_with_adetailer
Enhance face with adetailer
false
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.3
detail
Enhance/diminish detail while keeping the overall style/character
2
brightness
Adjust brightness
0.33
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
2516901206
input_image
Base image that the output should be generated from. This is useful when you want to add some detail to input_image. For example, if prompt is "sunglasses" and input_image has a man, there is the man wearing sunglasses in the output.
https://files.tungsten.run/uploads/902cf52656824ac6acc7914b58c8e513/DST-Select-Black-Hole-042%20(1).jpg
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
0.58
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
https://files.tungsten.run/uploads/7345e24b978c436ebe386ec90f5167c0/RDT_20240305_2052147481440688601942127.jpg
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
0.46
reference_pose_image
Image with a reference pose
https://files.tungsten.run/uploads/6af85bbc3b5a47218ae7f2cceefcd847/RDT_20240305_2052297582869007053034729.jpg
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
0.58
reference_depth_image
Image with a reference depth
https://files.tungsten.run/uploads/e8ef0c0ec04f4104b837c4bd726544c3/RDT_20240305_2052147481440688601942127.jpg
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
1
sampler
Sampler type
DPM++ 3M SDE Karras
samping_steps
Number of denoising steps
80
cfg_scale
Scale for classifier-free guidance
10
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
sdxl_vae.safetensors
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
true
Output
https://files.tungsten.run/uploads/cd9f0eafb6c44f08924c2a21f2a71240/00000-2516901206.png
https://files.tungsten.run/uploads/9eed2b963ad84c7f845f36c699b88ba9/00001-2516901207.png
https://files.tungsten.run/uploads/56d6008315404d47bf2201084d3d6cbc/00002-2516901208.png
Finished in 206.6 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: RAW Photography, breathtaking cinematic film still of Maximillian, a giant deadly RED robot with a SINGLE bright glowing RED LED EYE from The Black Hole, terrifying, imposing, whirring blades for hands, evil red eye beam glow, spaceship in background, professional, award-winning, highly detailed, realistic, intricate details, 8k, masterpiece, dynamic play of light, 35mm photograph, kodachrome, dust particles caught in the light, raytracing, RTX, 8K, 4K, HDRI, UHD, extremely detailed, intricately detailed, studio quality, film quality, perfect lighting, perfect shadows, perfect textures, antialiasing, volumetric fog, detailed background, holding gun, photorealistic, lifelike, <lora:add-detail-xl:2.0>, <lora:TLS:0.33> Full negative prompt: low quality, low resolution, low detail, out of focus, smudged, smeared, unrefined, unfinished, blurry, pixelated, artifacts, compression, JPEG Loading model: controlnetxlCNXL_tencentarcOpenpose [18cb12c1] Loaded state_dict from [/tungsten/models/ControlNet/controlnetxlCNXL_tencentarcOpenpose.safetensors] t2i_adapter_config ControlNet model controlnetxlCNXL_tencentarcOpenpose [18cb12c1] loaded. Loading preprocessor: openpose preprocessor resolution = 512 ControlNet preprocessor location: /tungsten/models/ControlNetAnnotators Loading model: controlnetxlCNXL_tencentarcDepthMidas [5752dddf] Loaded state_dict from [/tungsten/models/ControlNet/controlnetxlCNXL_tencentarcDepthMidas.safetensors] t2i_adapter_config ControlNet model controlnetxlCNXL_tencentarcDepthMidas [5752dddf] loaded. Loading preprocessor: depth preprocessor resolution = 512 Loading preprocessor: reference_only preprocessor resolution = -1 ControlNet Hooked - Time = 13.266228199005127 0%| | 0/47 [00:00<?, ?it/s]ControlNet used torch.float32 VAE to encode torch.Size([1, 4, 128, 128]). 2%|▏ | 1/47 [00:06<04:56, 6.45s/it] 4%|▍ | 2/47 [00:10<03:50, 5.12s/it] 6%|▋ | 3/47 [00:14<03:25, 4.67s/it] 9%|▊ | 4/47 [00:18<03:11, 4.46s/it] 11%|█ | 5/47 [00:22<03:01, 4.31s/it] 13%|█▎ | 6/47 [00:27<02:54, 4.26s/it] 15%|█▍ | 7/47 [00:30<02:44, 4.12s/it] 17%|█▋ | 8/47 [00:34<02:35, 3.99s/it] 19%|█▉ | 9/47 [00:38<02:32, 4.01s/it] 21%|██▏ | 10/47 [00:42<02:29, 4.05s/it] 23%|██▎ | 11/47 [00:46<02:23, 3.98s/it] 26%|██▌ | 12/47 [00:50<02:19, 4.00s/it] 28%|██▊ | 13/47 [00:54<02:15, 3.97s/it] 30%|██▉ | 14/47 [00:58<02:10, 3.97s/it] 32%|███▏ | 15/47 [01:02<02:08, 4.00s/it] 34%|███▍ | 16/47 [01:06<02:03, 3.97s/it] 36%|███▌ | 17/47 [01:10<02:00, 4.01s/it] 38%|███▊ | 18/47 [01:14<01:54, 3.96s/it] 40%|████ | 19/47 [01:18<01:49, 3.91s/it] 43%|████▎ | 20/47 [01:22<01:45, 3.89s/it] 45%|████▍ | 21/47 [01:25<01:40, 3.87s/it] 47%|████▋ | 22/47 [01:29<01:35, 3.83s/it] 49%|████▉ | 23/47 [01:33<01:32, 3.87s/it] 51%|█████ | 24/47 [01:37<01:28, 3.86s/it] 53%|█████▎ | 25/47 [01:41<01:25, 3.87s/it] 55%|█████▌ | 26/47 [01:45<01:19, 3.80s/it] 57%|█████▋ | 27/47 [01:48<01:16, 3.83s/it] 60%|█████▉ | 28/47 [01:52<01:13, 3.85s/it] 62%|██████▏ | 29/47 [01:56<01:08, 3.82s/it] 64%|██████▍ | 30/47 [02:00<01:05, 3.84s/it] 66%|██████▌ | 31/47 [02:04<01:01, 3.82s/it] 68%|██████▊ | 32/47 [02:07<00:56, 3.76s/it] 70%|███████ | 33/47 [02:11<00:54, 3.86s/it] 72%|███████▏ | 34/47 [02:15<00:50, 3.88s/it] 74%|███████▍ | 35/47 [02:19<00:45, 3.77s/it] 77%|███████▋ | 36/47 [02:22<00:40, 3.69s/it] 79%|███████▊ | 37/47 [02:26<00:36, 3.69s/it] 81%|████████ | 38/47 [02:30<00:33, 3.78s/it] 83%|████████▎ | 39/47 [02:34<00:29, 3.73s/it] 85%|████████▌ | 40/47 [02:37<00:25, 3.67s/it] 87%|████████▋ | 41/47 [02:41<00:22, 3.75s/it] 89%|████████▉ | 42/47 [02:45<00:18, 3.70s/it] 91%|█████████▏| 43/47 [02:48<00:14, 3.64s/it] 94%|█████████▎| 44/47 [02:52<00:11, 3.72s/it] 96%|█████████▌| 45/47 [02:56<00:07, 3.63s/it] 98%|█████████▊| 46/47 [02:58<00:03, 3.40s/it] 100%|██████████| 47/47 [03:01<00:00, 3.18s/it] 100%|██████████| 47/47 [03:01<00:00, 3.86s/it] Decoding latents in cuda:0... done in 2.41s Move latents to cpu... done in 0.01s Uploading outputs... Finished.
prompt
Specify things to see in the output
RAW Photography, breathtaking cinematic film still of Maximillian, a giant deadly RED robot with a SINGLE bright glowing RED LED EYE from The Black Hole, terrifying, imposing, whirring blades for hands, evil red eye beam glow, spaceship in background, professional, award-winning, highly detailed, realistic, intricate details, 8k, masterpiece, dynamic play of light, 35mm photograph, kodachrome, dust particles caught in the light, raytracing, RTX, 8K, 4K, HDRI, UHD, extremely detailed, intricately detailed, studio quality, film quality, perfect lighting, perfect shadows, perfect textures, antialiasing, volumetric fog, detailed background, holding gun, photorealistic, lifelike
negative_prompt
Specify things to not see in the output
low quality, low resolution, low detail, out of focus, smudged, smeared, unrefined, unfinished, blurry, pixelated, artifacts, compression, JPEG
num_outputs
Number of output images
3
width
Output image width
1024
height
Output image height
1024
enhance_face_with_adetailer
Enhance face with adetailer
false
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.3
detail
Enhance/diminish detail while keeping the overall style/character
2
brightness
Adjust brightness
0.33
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
2516901206
input_image
Base image that the output should be generated from. This is useful when you want to add some detail to input_image. For example, if prompt is "sunglasses" and input_image has a man, there is the man wearing sunglasses in the output.
https://files.tungsten.run/uploads/902cf52656824ac6acc7914b58c8e513/DST-Select-Black-Hole-042%20(1).jpg
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
0.58
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
https://files.tungsten.run/uploads/7345e24b978c436ebe386ec90f5167c0/RDT_20240305_2052147481440688601942127.jpg
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
0.46
reference_pose_image
Image with a reference pose
https://files.tungsten.run/uploads/6af85bbc3b5a47218ae7f2cceefcd847/RDT_20240305_2052297582869007053034729.jpg
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
0.58
reference_depth_image
Image with a reference depth
https://files.tungsten.run/uploads/e8ef0c0ec04f4104b837c4bd726544c3/RDT_20240305_2052147481440688601942127.jpg
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
1
sampler
Sampler type
DPM++ 3M SDE Karras
samping_steps
Number of denoising steps
80
cfg_scale
Scale for classifier-free guidance
10
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
sdxl_vae.safetensors
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
true
https://files.tungsten.run/uploads/cd9f0eafb6c44f08924c2a21f2a71240/00000-2516901206.png
https://files.tungsten.run/uploads/9eed2b963ad84c7f845f36c699b88ba9/00001-2516901207.png
https://files.tungsten.run/uploads/56d6008315404d47bf2201084d3d6cbc/00002-2516901208.png
Finished in 206.6 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: RAW Photography, breathtaking cinematic film still of Maximillian, a giant deadly RED robot with a SINGLE bright glowing RED LED EYE from The Black Hole, terrifying, imposing, whirring blades for hands, evil red eye beam glow, spaceship in background, professional, award-winning, highly detailed, realistic, intricate details, 8k, masterpiece, dynamic play of light, 35mm photograph, kodachrome, dust particles caught in the light, raytracing, RTX, 8K, 4K, HDRI, UHD, extremely detailed, intricately detailed, studio quality, film quality, perfect lighting, perfect shadows, perfect textures, antialiasing, volumetric fog, detailed background, holding gun, photorealistic, lifelike, <lora:add-detail-xl:2.0>, <lora:TLS:0.33> Full negative prompt: low quality, low resolution, low detail, out of focus, smudged, smeared, unrefined, unfinished, blurry, pixelated, artifacts, compression, JPEG Loading model: controlnetxlCNXL_tencentarcOpenpose [18cb12c1] Loaded state_dict from [/tungsten/models/ControlNet/controlnetxlCNXL_tencentarcOpenpose.safetensors] t2i_adapter_config ControlNet model controlnetxlCNXL_tencentarcOpenpose [18cb12c1] loaded. Loading preprocessor: openpose preprocessor resolution = 512 ControlNet preprocessor location: /tungsten/models/ControlNetAnnotators Loading model: controlnetxlCNXL_tencentarcDepthMidas [5752dddf] Loaded state_dict from [/tungsten/models/ControlNet/controlnetxlCNXL_tencentarcDepthMidas.safetensors] t2i_adapter_config ControlNet model controlnetxlCNXL_tencentarcDepthMidas [5752dddf] loaded. Loading preprocessor: depth preprocessor resolution = 512 Loading preprocessor: reference_only preprocessor resolution = -1 ControlNet Hooked - Time = 13.266228199005127 0%| | 0/47 [00:00<?, ?it/s]ControlNet used torch.float32 VAE to encode torch.Size([1, 4, 128, 128]). 2%|▏ | 1/47 [00:06<04:56, 6.45s/it] 4%|▍ | 2/47 [00:10<03:50, 5.12s/it] 6%|▋ | 3/47 [00:14<03:25, 4.67s/it] 9%|▊ | 4/47 [00:18<03:11, 4.46s/it] 11%|█ | 5/47 [00:22<03:01, 4.31s/it] 13%|█▎ | 6/47 [00:27<02:54, 4.26s/it] 15%|█▍ | 7/47 [00:30<02:44, 4.12s/it] 17%|█▋ | 8/47 [00:34<02:35, 3.99s/it] 19%|█▉ | 9/47 [00:38<02:32, 4.01s/it] 21%|██▏ | 10/47 [00:42<02:29, 4.05s/it] 23%|██▎ | 11/47 [00:46<02:23, 3.98s/it] 26%|██▌ | 12/47 [00:50<02:19, 4.00s/it] 28%|██▊ | 13/47 [00:54<02:15, 3.97s/it] 30%|██▉ | 14/47 [00:58<02:10, 3.97s/it] 32%|███▏ | 15/47 [01:02<02:08, 4.00s/it] 34%|███▍ | 16/47 [01:06<02:03, 3.97s/it] 36%|███▌ | 17/47 [01:10<02:00, 4.01s/it] 38%|███▊ | 18/47 [01:14<01:54, 3.96s/it] 40%|████ | 19/47 [01:18<01:49, 3.91s/it] 43%|████▎ | 20/47 [01:22<01:45, 3.89s/it] 45%|████▍ | 21/47 [01:25<01:40, 3.87s/it] 47%|████▋ | 22/47 [01:29<01:35, 3.83s/it] 49%|████▉ | 23/47 [01:33<01:32, 3.87s/it] 51%|█████ | 24/47 [01:37<01:28, 3.86s/it] 53%|█████▎ | 25/47 [01:41<01:25, 3.87s/it] 55%|█████▌ | 26/47 [01:45<01:19, 3.80s/it] 57%|█████▋ | 27/47 [01:48<01:16, 3.83s/it] 60%|█████▉ | 28/47 [01:52<01:13, 3.85s/it] 62%|██████▏ | 29/47 [01:56<01:08, 3.82s/it] 64%|██████▍ | 30/47 [02:00<01:05, 3.84s/it] 66%|██████▌ | 31/47 [02:04<01:01, 3.82s/it] 68%|██████▊ | 32/47 [02:07<00:56, 3.76s/it] 70%|███████ | 33/47 [02:11<00:54, 3.86s/it] 72%|███████▏ | 34/47 [02:15<00:50, 3.88s/it] 74%|███████▍ | 35/47 [02:19<00:45, 3.77s/it] 77%|███████▋ | 36/47 [02:22<00:40, 3.69s/it] 79%|███████▊ | 37/47 [02:26<00:36, 3.69s/it] 81%|████████ | 38/47 [02:30<00:33, 3.78s/it] 83%|████████▎ | 39/47 [02:34<00:29, 3.73s/it] 85%|████████▌ | 40/47 [02:37<00:25, 3.67s/it] 87%|████████▋ | 41/47 [02:41<00:22, 3.75s/it] 89%|████████▉ | 42/47 [02:45<00:18, 3.70s/it] 91%|█████████▏| 43/47 [02:48<00:14, 3.64s/it] 94%|█████████▎| 44/47 [02:52<00:11, 3.72s/it] 96%|█████████▌| 45/47 [02:56<00:07, 3.63s/it] 98%|█████████▊| 46/47 [02:58<00:03, 3.40s/it] 100%|██████████| 47/47 [03:01<00:00, 3.18s/it] 100%|██████████| 47/47 [03:01<00:00, 3.86s/it] Decoding latents in cuda:0... done in 2.41s Move latents to cpu... done in 0.01s Uploading outputs... Finished.