tungsten-logo
Sign In
Dragon Tamer with REMERetroRefinedXL
REMERetroRefinedXL:v1.0
sparks
sparks
·
Mar 23
349
Input
prompt
Specify things to see in the output
A dragon tamer perched on a cliff edge, signaling to a group of dragons flying against the backdrop of a setting sun, with a small, mischievous dragonling playing at their feet.
negative_prompt
Specify things to not see in the output
EnvyBetterHiresFixXL01
Envy Better Hires Fix Xl01
0.5
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.
0
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
7
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/5e78743ab4f54fa89901f0802c33e977/00000-0.webp
https://files.tungsten.run/uploads/44d1acfd27564f3086f175e2ce53644a/00001-1.webp
https://files.tungsten.run/uploads/de009372037d4ff08e89facac0791e92/00002-2.webp
Finished in 107.0 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: A dragon tamer perched on a cliff edge, signaling to a group of dragons flying against the backdrop of a setting sun, with a small, mischievous dragonling playing at their feet., <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: 0%| | 0/38 [00:00<?, ?it/s] 3%|▎ | 1/38 [00:03<02:24, 3.91s/it] 5%|▌ | 2/38 [00:06<01:47, 2.99s/it] 8%|▊ | 3/38 [00:08<01:38, 2.81s/it] 11%|█ | 4/38 [00:11<01:34, 2.77s/it] 13%|█▎ | 5/38 [00:14<01:30, 2.73s/it] 16%|█▌ | 6/38 [00:17<01:29, 2.79s/it] 18%|█▊ | 7/38 [00:19<01:26, 2.79s/it] 21%|██ | 8/38 [00:22<01:23, 2.80s/it] 24%|██▎ | 9/38 [00:25<01:20, 2.78s/it] 26%|██▋ | 10/38 [00:28<01:17, 2.77s/it] 29%|██▉ | 11/38 [00:30<01:12, 2.68s/it] 32%|███▏ | 12/38 [00:33<01:09, 2.66s/it] 34%|███▍ | 13/38 [00:36<01:07, 2.71s/it] 37%|███▋ | 14/38 [00:38<01:05, 2.75s/it] 39%|███▉ | 15/38 [00:41<01:03, 2.77s/it] 42%|████▏ | 16/38 [00:44<01:00, 2.73s/it] 45%|████▍ | 17/38 [00:47<00:58, 2.78s/it] 47%|████▋ | 18/38 [00:49<00:53, 2.70s/it] 50%|█████ | 19/38 [00:52<00:49, 2.59s/it] 53%|█████▎ | 20/38 [00:54<00:46, 2.61s/it] 55%|█████▌ | 21/38 [00:57<00:44, 2.64s/it] 58%|█████▊ | 22/38 [01:00<00:42, 2.68s/it] 61%|██████ | 23/38 [01:03<00:40, 2.70s/it] 63%|██████▎ | 24/38 [01:05<00:36, 2.64s/it] 66%|██████▌ | 25/38 [01:08<00:34, 2.69s/it] 68%|██████▊ | 26/38 [01:10<00:32, 2.67s/it] 71%|███████ | 27/38 [01:13<00:28, 2.62s/it] 74%|███████▎ | 28/38 [01:16<00:26, 2.67s/it] 76%|███████▋ | 29/38 [01:18<00:23, 2.62s/it] 79%|███████▉ | 30/38 [01:21<00:20, 2.55s/it] 82%|████████▏ | 31/38 [01:23<00:17, 2.57s/it] 84%|████████▍ | 32/38 [01:26<00:15, 2.52s/it] 87%|████████▋ | 33/38 [01:28<00:12, 2.53s/it] 89%|████████▉ | 34/38 [01:30<00:09, 2.44s/it] 92%|█████████▏| 35/38 [01:33<00:07, 2.44s/it] 95%|█████████▍| 36/38 [01:35<00:04, 2.36s/it] 97%|█████████▋| 37/38 [01:37<00:02, 2.13s/it] 100%|██████████| 38/38 [01:38<00:00, 1.89s/it] 100%|██████████| 38/38 [01:38<00:00, 2.59s/it] Decoding latents in cuda:0... done in 2.39s Move latents to cpu... done in 0.03s
prompt
Specify things to see in the output
A dragon tamer perched on a cliff edge, signaling to a group of dragons flying against the backdrop of a setting sun, with a small, mischievous dragonling playing at their feet.
negative_prompt
Specify things to not see in the output
EnvyBetterHiresFixXL01
Envy Better Hires Fix Xl01
0.5
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.
0
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
7
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/5e78743ab4f54fa89901f0802c33e977/00000-0.webp
https://files.tungsten.run/uploads/44d1acfd27564f3086f175e2ce53644a/00001-1.webp
https://files.tungsten.run/uploads/de009372037d4ff08e89facac0791e92/00002-2.webp
Finished in 107.0 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: A dragon tamer perched on a cliff edge, signaling to a group of dragons flying against the backdrop of a setting sun, with a small, mischievous dragonling playing at their feet., <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: 0%| | 0/38 [00:00<?, ?it/s] 3%|▎ | 1/38 [00:03<02:24, 3.91s/it] 5%|▌ | 2/38 [00:06<01:47, 2.99s/it] 8%|▊ | 3/38 [00:08<01:38, 2.81s/it] 11%|█ | 4/38 [00:11<01:34, 2.77s/it] 13%|█▎ | 5/38 [00:14<01:30, 2.73s/it] 16%|█▌ | 6/38 [00:17<01:29, 2.79s/it] 18%|█▊ | 7/38 [00:19<01:26, 2.79s/it] 21%|██ | 8/38 [00:22<01:23, 2.80s/it] 24%|██▎ | 9/38 [00:25<01:20, 2.78s/it] 26%|██▋ | 10/38 [00:28<01:17, 2.77s/it] 29%|██▉ | 11/38 [00:30<01:12, 2.68s/it] 32%|███▏ | 12/38 [00:33<01:09, 2.66s/it] 34%|███▍ | 13/38 [00:36<01:07, 2.71s/it] 37%|███▋ | 14/38 [00:38<01:05, 2.75s/it] 39%|███▉ | 15/38 [00:41<01:03, 2.77s/it] 42%|████▏ | 16/38 [00:44<01:00, 2.73s/it] 45%|████▍ | 17/38 [00:47<00:58, 2.78s/it] 47%|████▋ | 18/38 [00:49<00:53, 2.70s/it] 50%|█████ | 19/38 [00:52<00:49, 2.59s/it] 53%|█████▎ | 20/38 [00:54<00:46, 2.61s/it] 55%|█████▌ | 21/38 [00:57<00:44, 2.64s/it] 58%|█████▊ | 22/38 [01:00<00:42, 2.68s/it] 61%|██████ | 23/38 [01:03<00:40, 2.70s/it] 63%|██████▎ | 24/38 [01:05<00:36, 2.64s/it] 66%|██████▌ | 25/38 [01:08<00:34, 2.69s/it] 68%|██████▊ | 26/38 [01:10<00:32, 2.67s/it] 71%|███████ | 27/38 [01:13<00:28, 2.62s/it] 74%|███████▎ | 28/38 [01:16<00:26, 2.67s/it] 76%|███████▋ | 29/38 [01:18<00:23, 2.62s/it] 79%|███████▉ | 30/38 [01:21<00:20, 2.55s/it] 82%|████████▏ | 31/38 [01:23<00:17, 2.57s/it] 84%|████████▍ | 32/38 [01:26<00:15, 2.52s/it] 87%|████████▋ | 33/38 [01:28<00:12, 2.53s/it] 89%|████████▉ | 34/38 [01:30<00:09, 2.44s/it] 92%|█████████▏| 35/38 [01:33<00:07, 2.44s/it] 95%|█████████▍| 36/38 [01:35<00:04, 2.36s/it] 97%|█████████▋| 37/38 [01:37<00:02, 2.13s/it] 100%|██████████| 38/38 [01:38<00:00, 1.89s/it] 100%|██████████| 38/38 [01:38<00:00, 2.59s/it] Decoding latents in cuda:0... done in 2.39s Move latents to cpu... done in 0.03s