tungsten-logo
Sign In
Yellow Machine
REME Retro Redux XL:v1.0
sparks
sparks
·
Mar 20
367
Input
prompt
Specify things to see in the output
a four meter tall yellow drdnght machine with rocket launcher and flamethrower walks across an alien battlefield searching for enemies, rockets streak across the sky and explode into the landscape
negative_prompt
Specify things to not see in the output
EnvyBetterHiresFixXL01
Envy Better Hires Fix Xl01
0
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
0.55
detail
Enhance/diminish detail while keeping the overall style/character
1
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
-1
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.
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
0.55
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
1
reference_pose_image
Image with a reference pose
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
1
reference_depth_image
Image with a reference depth
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
1
sampler
Sampler type
DPM++ 2M SDE Karras
samping_steps
Number of denoising steps
38
cfg_scale
Scale for classifier-free guidance
6
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.
false
Output
https://files.tungsten.run/uploads/40f0b02149a942e7bcaaa31a5e16736f/00000-4015179447.webp
https://files.tungsten.run/uploads/9ea883688d3647509579d146a6dd2f05/00001-4015179448.webp
https://files.tungsten.run/uploads/9e0de35f4464478f94698bf539e26c30/00002-4015179449.webp
Finished in 107.7 seconds
Setting up the model... Preparing inputs... Processing... Using seed 4015179447 Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: a four meter tall yellow drdnght machine with rocket launcher and flamethrower walks across an alien battlefield searching for enemies, rockets streak across the sky and explode into the landscape, <lora:add-detail-xl:1.0> Full negative prompt: 0%| | 0/38 [00:00<?, ?it/s] 3%|▎ | 1/38 [00:03<02:14, 3.62s/it] 5%|▌ | 2/38 [00:06<01:51, 3.10s/it] 8%|▊ | 3/38 [00:09<01:45, 3.01s/it] 11%|█ | 4/38 [00:12<01:45, 3.12s/it] 13%|█▎ | 5/38 [00:15<01:39, 3.02s/it] 16%|█▌ | 6/38 [00:18<01:35, 2.99s/it] 18%|█▊ | 7/38 [00:21<01:31, 2.95s/it] 21%|██ | 8/38 [00:24<01:28, 2.94s/it] 24%|██▎ | 9/38 [00:26<01:23, 2.89s/it] 26%|██▋ | 10/38 [00:29<01:20, 2.86s/it] 29%|██▉ | 11/38 [00:32<01:14, 2.75s/it] 32%|███▏ | 12/38 [00:34<01:10, 2.72s/it] 34%|███▍ | 13/38 [00:37<01:09, 2.78s/it] 37%|███▋ | 14/38 [00:40<01:07, 2.81s/it] 39%|███▉ | 15/38 [00:43<01:04, 2.82s/it] 42%|████▏ | 16/38 [00:46<01:00, 2.77s/it] 45%|████▍ | 17/38 [00:49<00:59, 2.84s/it] 47%|████▋ | 18/38 [00:51<00:54, 2.74s/it] 50%|█████ | 19/38 [00:53<00:49, 2.63s/it] 53%|█████▎ | 20/38 [00:56<00:47, 2.64s/it] 55%|█████▌ | 21/38 [00:59<00:45, 2.67s/it] 58%|█████▊ | 22/38 [01:02<00:43, 2.69s/it] 61%|██████ | 23/38 [01:04<00:40, 2.71s/it] 63%|██████▎ | 24/38 [01:07<00:37, 2.67s/it] 66%|██████▌ | 25/38 [01:10<00:35, 2.71s/it] 68%|██████▊ | 26/38 [01:12<00:32, 2.68s/it] 71%|███████ | 27/38 [01:15<00:28, 2.63s/it] 74%|███████▎ | 28/38 [01:18<00:26, 2.68s/it] 76%|███████▋ | 29/38 [01:20<00:23, 2.62s/it] 79%|███████▉ | 30/38 [01:23<00:20, 2.56s/it] 82%|████████▏ | 31/38 [01:25<00:17, 2.57s/it] 84%|████████▍ | 32/38 [01:28<00:15, 2.54s/it] 87%|████████▋ | 33/38 [01:30<00:12, 2.54s/it] 89%|████████▉ | 34/38 [01:32<00:09, 2.45s/it] 92%|█████████▏| 35/38 [01:35<00:07, 2.47s/it] 95%|█████████▍| 36/38 [01:37<00:04, 2.40s/it] 97%|█████████▋| 37/38 [01:39<00:02, 2.17s/it] 100%|██████████| 38/38 [01:40<00:00, 1.92s/it] 100%|██████████| 38/38 [01:40<00:00, 2.65s/it] Decoding latents in cuda:0... done in 2.42s Move latents to cpu... done in 0.03s
prompt
Specify things to see in the output
a four meter tall yellow drdnght machine with rocket launcher and flamethrower walks across an alien battlefield searching for enemies, rockets streak across the sky and explode into the landscape
negative_prompt
Specify things to not see in the output
EnvyBetterHiresFixXL01
Envy Better Hires Fix Xl01
0
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
0.55
detail
Enhance/diminish detail while keeping the overall style/character
1
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
-1
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.
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
0.55
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
1
reference_pose_image
Image with a reference pose
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
1
reference_depth_image
Image with a reference depth
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
1
sampler
Sampler type
DPM++ 2M SDE Karras
samping_steps
Number of denoising steps
38
cfg_scale
Scale for classifier-free guidance
6
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.
false
https://files.tungsten.run/uploads/40f0b02149a942e7bcaaa31a5e16736f/00000-4015179447.webp
https://files.tungsten.run/uploads/9ea883688d3647509579d146a6dd2f05/00001-4015179448.webp
https://files.tungsten.run/uploads/9e0de35f4464478f94698bf539e26c30/00002-4015179449.webp
Finished in 107.7 seconds
Setting up the model... Preparing inputs... Processing... Using seed 4015179447 Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: a four meter tall yellow drdnght machine with rocket launcher and flamethrower walks across an alien battlefield searching for enemies, rockets streak across the sky and explode into the landscape, <lora:add-detail-xl:1.0> Full negative prompt: 0%| | 0/38 [00:00<?, ?it/s] 3%|▎ | 1/38 [00:03<02:14, 3.62s/it] 5%|▌ | 2/38 [00:06<01:51, 3.10s/it] 8%|▊ | 3/38 [00:09<01:45, 3.01s/it] 11%|█ | 4/38 [00:12<01:45, 3.12s/it] 13%|█▎ | 5/38 [00:15<01:39, 3.02s/it] 16%|█▌ | 6/38 [00:18<01:35, 2.99s/it] 18%|█▊ | 7/38 [00:21<01:31, 2.95s/it] 21%|██ | 8/38 [00:24<01:28, 2.94s/it] 24%|██▎ | 9/38 [00:26<01:23, 2.89s/it] 26%|██▋ | 10/38 [00:29<01:20, 2.86s/it] 29%|██▉ | 11/38 [00:32<01:14, 2.75s/it] 32%|███▏ | 12/38 [00:34<01:10, 2.72s/it] 34%|███▍ | 13/38 [00:37<01:09, 2.78s/it] 37%|███▋ | 14/38 [00:40<01:07, 2.81s/it] 39%|███▉ | 15/38 [00:43<01:04, 2.82s/it] 42%|████▏ | 16/38 [00:46<01:00, 2.77s/it] 45%|████▍ | 17/38 [00:49<00:59, 2.84s/it] 47%|████▋ | 18/38 [00:51<00:54, 2.74s/it] 50%|█████ | 19/38 [00:53<00:49, 2.63s/it] 53%|█████▎ | 20/38 [00:56<00:47, 2.64s/it] 55%|█████▌ | 21/38 [00:59<00:45, 2.67s/it] 58%|█████▊ | 22/38 [01:02<00:43, 2.69s/it] 61%|██████ | 23/38 [01:04<00:40, 2.71s/it] 63%|██████▎ | 24/38 [01:07<00:37, 2.67s/it] 66%|██████▌ | 25/38 [01:10<00:35, 2.71s/it] 68%|██████▊ | 26/38 [01:12<00:32, 2.68s/it] 71%|███████ | 27/38 [01:15<00:28, 2.63s/it] 74%|███████▎ | 28/38 [01:18<00:26, 2.68s/it] 76%|███████▋ | 29/38 [01:20<00:23, 2.62s/it] 79%|███████▉ | 30/38 [01:23<00:20, 2.56s/it] 82%|████████▏ | 31/38 [01:25<00:17, 2.57s/it] 84%|████████▍ | 32/38 [01:28<00:15, 2.54s/it] 87%|████████▋ | 33/38 [01:30<00:12, 2.54s/it] 89%|████████▉ | 34/38 [01:32<00:09, 2.45s/it] 92%|█████████▏| 35/38 [01:35<00:07, 2.47s/it] 95%|█████████▍| 36/38 [01:37<00:04, 2.40s/it] 97%|█████████▋| 37/38 [01:39<00:02, 2.17s/it] 100%|██████████| 38/38 [01:40<00:00, 1.92s/it] 100%|██████████| 38/38 [01:40<00:00, 2.65s/it] Decoding latents in cuda:0... done in 2.42s Move latents to cpu... done in 0.03s