tungsten-logo
Sign In
Alita with Delta
delta:v1.1
sparks
sparks
·
Feb 26
346
Input
prompt
Specify things to see in the output
<lora:LCMTurboMix_DPM_SDE_Karras:1>, cinematic photo AND Hyperrealistic art, a woman in a blue costume with purple hair and blue eyes, alternate hairstyle, bisexual lighting, still from alita, blue and purple lighting, super saiyan sonic movie poster, official concept art, official artwork hdr, cool purple lighting, epic cold blue lighting, concept art for movie, big glowing netflix logo behind, purple lightning, movie still of robot goku, movie concept art . 35mm photograph, film, bokeh, professional, 4k, highly detailed
negative_prompt
Specify things to not see in the output
drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, simplified, abstract, unrealistic, impressionistic, low resolution, ear, Middle Ages,, deformed, ugly, flat, low contrast, oversaturated, underexposed, overexposed, blurred, noisy, bad anatomy, bad hands, three hands, three legs, bad arms, missing arms, missing fingers, extra fingers, ugly fingers, long fingers, horn, amputation, disconnected limbs, wrong, blur, blurry, out of focus,
num_outputs
Number of output images
3
width
Output image width
960
height
Output image height
1280
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.
4048288339
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++ SDE Karras
samping_steps
Number of denoising steps
8
cfg_scale
Scale for classifier-free guidance
2
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>
LCMTurboMix_DPM_SDE_Karras.safetensors
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/5c815d141bee40678f0baed99f7c156c/00000-4048288339.webp
https://files.tungsten.run/uploads/adf39f456158489086c116b1c2eacde6/00001-4048288340.webp
https://files.tungsten.run/uploads/2cfe4aa6e7ea476cb4c8a806073498a6/00002-4048288341.webp
Finished in 77.0 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: <lora:LCMTurboMix_DPM_SDE_Karras:1>, cinematic photo AND Hyperrealistic art, a woman in a blue costume with purple hair and blue eyes, alternate hairstyle, bisexual lighting, still from alita, blue and purple lighting, super saiyan sonic movie poster, official concept art, official artwork hdr, cool purple lighting, epic cold blue lighting, concept art for movie, big glowing netflix logo behind, purple lightning, movie still of robot goku, movie concept art . 35mm photograph, film, bokeh, professional, 4k, highly detailed, <lora:add-detail-xl:1.0> Full negative prompt: drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, simplified, abstract, unrealistic, impressionistic, low resolution, ear, Middle Ages,, deformed, ugly, flat, low contrast, oversaturated, underexposed, overexposed, blurred, noisy, bad anatomy, bad hands, three hands, three legs, bad arms, missing arms, missing fingers, extra fingers, ugly fingers, long fingers, horn, amputation, disconnected limbs, wrong, blur, blurry, out of focus, Failed to match keys when loading network /tungsten/models/Lora/LCMTurboMix_DPM_SDE_Karras.safetensors: {'lora_unet_up_blocks_0_upsamplers_0_conv.alpha': 'diffusion_model_up_blocks_0_upsamplers_0_conv', 'lora_unet_up_blocks_0_upsamplers_0_conv.lora_down.weight': 'diffusion_model_up_blocks_0_upsamplers_0_conv', 'lora_unet_up_blocks_0_upsamplers_0_conv.lora_up.weight': 'diffusion_model_up_blocks_0_upsamplers_0_conv'} 0%| | 0/8 [00:00<?, ?it/s] 12%|█▎ | 1/8 [00:08<00:59, 8.52s/it] 25%|██▌ | 2/8 [00:17<00:53, 8.97s/it] 38%|███▊ | 3/8 [00:27<00:47, 9.49s/it] 50%|█████ | 4/8 [00:36<00:37, 9.25s/it] 62%|██████▎ | 5/8 [00:45<00:27, 9.12s/it] 75%|███████▌ | 6/8 [00:53<00:17, 8.83s/it] 88%|████████▊ | 7/8 [01:00<00:08, 8.06s/it] 100%|██████████| 8/8 [01:03<00:00, 6.32s/it] 100%|██████████| 8/8 [01:03<00:00, 7.88s/it] Decoding latents in cuda:0... done in 2.9s Move latents to cpu... done in 0.03s Uploading outputs... Finished.
prompt
Specify things to see in the output
<lora:LCMTurboMix_DPM_SDE_Karras:1>, cinematic photo AND Hyperrealistic art, a woman in a blue costume with purple hair and blue eyes, alternate hairstyle, bisexual lighting, still from alita, blue and purple lighting, super saiyan sonic movie poster, official concept art, official artwork hdr, cool purple lighting, epic cold blue lighting, concept art for movie, big glowing netflix logo behind, purple lightning, movie still of robot goku, movie concept art . 35mm photograph, film, bokeh, professional, 4k, highly detailed
negative_prompt
Specify things to not see in the output
drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, simplified, abstract, unrealistic, impressionistic, low resolution, ear, Middle Ages,, deformed, ugly, flat, low contrast, oversaturated, underexposed, overexposed, blurred, noisy, bad anatomy, bad hands, three hands, three legs, bad arms, missing arms, missing fingers, extra fingers, ugly fingers, long fingers, horn, amputation, disconnected limbs, wrong, blur, blurry, out of focus,
num_outputs
Number of output images
3
width
Output image width
960
height
Output image height
1280
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.
4048288339
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++ SDE Karras
samping_steps
Number of denoising steps
8
cfg_scale
Scale for classifier-free guidance
2
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>
LCMTurboMix_DPM_SDE_Karras.safetensors
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/5c815d141bee40678f0baed99f7c156c/00000-4048288339.webp
https://files.tungsten.run/uploads/adf39f456158489086c116b1c2eacde6/00001-4048288340.webp
https://files.tungsten.run/uploads/2cfe4aa6e7ea476cb4c8a806073498a6/00002-4048288341.webp
Finished in 77.0 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: <lora:LCMTurboMix_DPM_SDE_Karras:1>, cinematic photo AND Hyperrealistic art, a woman in a blue costume with purple hair and blue eyes, alternate hairstyle, bisexual lighting, still from alita, blue and purple lighting, super saiyan sonic movie poster, official concept art, official artwork hdr, cool purple lighting, epic cold blue lighting, concept art for movie, big glowing netflix logo behind, purple lightning, movie still of robot goku, movie concept art . 35mm photograph, film, bokeh, professional, 4k, highly detailed, <lora:add-detail-xl:1.0> Full negative prompt: drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, simplified, abstract, unrealistic, impressionistic, low resolution, ear, Middle Ages,, deformed, ugly, flat, low contrast, oversaturated, underexposed, overexposed, blurred, noisy, bad anatomy, bad hands, three hands, three legs, bad arms, missing arms, missing fingers, extra fingers, ugly fingers, long fingers, horn, amputation, disconnected limbs, wrong, blur, blurry, out of focus, Failed to match keys when loading network /tungsten/models/Lora/LCMTurboMix_DPM_SDE_Karras.safetensors: {'lora_unet_up_blocks_0_upsamplers_0_conv.alpha': 'diffusion_model_up_blocks_0_upsamplers_0_conv', 'lora_unet_up_blocks_0_upsamplers_0_conv.lora_down.weight': 'diffusion_model_up_blocks_0_upsamplers_0_conv', 'lora_unet_up_blocks_0_upsamplers_0_conv.lora_up.weight': 'diffusion_model_up_blocks_0_upsamplers_0_conv'} 0%| | 0/8 [00:00<?, ?it/s] 12%|█▎ | 1/8 [00:08<00:59, 8.52s/it] 25%|██▌ | 2/8 [00:17<00:53, 8.97s/it] 38%|███▊ | 3/8 [00:27<00:47, 9.49s/it] 50%|█████ | 4/8 [00:36<00:37, 9.25s/it] 62%|██████▎ | 5/8 [00:45<00:27, 9.12s/it] 75%|███████▌ | 6/8 [00:53<00:17, 8.83s/it] 88%|████████▊ | 7/8 [01:00<00:08, 8.06s/it] 100%|██████████| 8/8 [01:03<00:00, 6.32s/it] 100%|██████████| 8/8 [01:03<00:00, 7.88s/it] Decoding latents in cuda:0... done in 2.9s Move latents to cpu... done in 0.03s Uploading outputs... Finished.