Model
Trends
.ai
Model
Trends
.ai
os melhores modelos de IA de código aberto
Executar localmente
lora_CleanLORA_Ellie_(TLOU_p1_Bake=SD1.5_epoch22.safetensors
144 MB · SafeTensor
Os downloads são servidos pelo Civitai. Alguns criadores pedem login no Civitai primeiro.
Sobre este modelo
STABLE DIFFUSION 1.5 · LoRAs
Criado por
_E_
no Civitai
This lora renders images of Ellie from The Last Of Us (game) Recommended settings for getting good renders: # Guidance at approx 7.0+ # Best weight around 0.15 - 0.2 # Works great with realistic and non-realistic models # works well with basic and elaborate prompts Sidenotes: # Seems to interact well with other loras # Render at low sizes and use /more /size /strength to upscale # for more real world renders use negative prompts like: dirt, bruises, backpack Example Prompt: /render 1girl, solo, , [worst quality, lowres, blurry]
Notas do criador
This is my own version of Ellie from The last of us (part 1). What's special about this LORA is that every training images are generated in Blender with original game model with complete white background, which results in every generations being constant and stable in quality. Thus naming it, CLEAN LORA. Images with most popular camera angles are prioritized in learning with minor camera angles still being learnt but with less repetition. Ensuring most generations resulting in good camera shots. 35 repetitions are portrait and upper body shots. 25 are full body shots. 15 are extreme angles and sitting, and character looking away. 3 bake versions are uploaded, AnyLora and Stable Diffusion v1.5 base. And then GhostMix v3 bake which is for using with GhostMix mainly. Prompts: TLOU_EW is an optional token that can be used in prompts but unnecessary. Use this to get your image closer to trained images. MUST PLACE (bruise, dirty:1.3) in NEGATIVES to produce clean face without artifacts. Recommended LORA strength = 0.5 ~ 0.6 Machine Learning Stats: Dimension = 512 x 768 (25 images x 35 repeats = 1015 steps) + (17 images x 25 repeats = 425 steps) + (21 images x 15 repeats = 315 steps) /3 batch process = 585 steps per epoch 585 steps x 22 epoch = 12870 total steps
Palavras-gatilho
TLOU_EW
581 downloads · 258 curtidas no Civitai
SHA256
B8E2FAEF14D5D89E47791183D2DB90CB79BBCE925A963D293E6F7C8213D1CDEA
ID de modelo ModelTrends.ai
#6307
Denunciar conteúdo
Renders de exemplo
Prompts e configurações compartilhados por quem fez estes renders no Civitai. Escolha um render para ver como foi feito.
Configurações
Sampler
DPM++ 2M Karras
Passos
32
Guidance
7
Seed
3982200558
Tamanho
512x768
Prompt
(best quality:1) , (masterpiece:1), (ultra detailed:1), TLOU_EW, photorealism, upper body, (looking at viewer:1.1), (scenery, ocean background:1.2) <lora:lora_TLOU_EW_1stTrialSD-1.5Full-000022:0.5>
Prompt negativo
(worst quality, low quality, button, buttons, dirty, bruise:1.3)
Configurações
Sampler
DPM++ 2S a Karras
Passos
26
Guidance
9
Seed
3203093320
Tamanho
512x800
Prompt
<lora:lora_TLOU_EW_5thAnyLORA:0> <lora:lora_TLOU_EW_4thGhostMix_AltSettings:0> <lora:lora_TLOU_EW_1stTrialSD-1.5Full:0.4> photo, face portrait, sony a7, 50 mm lens, (face closeup:1.3) petite skinny (14 years old girl), ellie from the last of us, (seductive:1), movie premiere gala, with photographers, public, <lyco:public_v3.0-locon:0.6>,by night (from above angle:0.8), in a balenciaga shiny (halter dress:1.1), sleeveless, eyeliner, (profile:1.3)(looking at the viewer:1.3), standing (contrapposto:1.3), waving, (Flonixprompt1)
Prompt negativo
(worst quality:2), (low quality:2), (normal quality:2), lowres, ((greyscale)), bad anatomy, extra arm, extra leg, disfigured, deformed, extra limbs, badhandv4, nipples, (dirt:1.4), backpack, (worst quality, low quality, difConsistency_negative_v2)
Configurações
Sampler
DPM++ 2M Karras
Passos
25
Guidance
6
Seed
4056553198
Tamanho
3072x4096
Prompt
RAW photo, high quality, high detailed, 8k, uhd, HDR
Prompt negativo
(worst quality:2), (low quality:2), (normal quality:2), lowres, ((greyscale)), bad anatomy, disfigured, deformed, (dirt:1.4), (worst quality, low quality), (bad_pictures), moles, cartoon, painting, illustration, (worst quality, low quality, normal quality:2), nipples, nsfw, (close-up, portrait)
Modelos de IA para geração de imagem, vídeo e texto
ellie tlou é um LoRA para a família Stable Diffusion 1.5 listado no ModelTrends.ai, um catálogo somente leitura de modelos de IA de código aberto para imagem, vídeo e texto. Compare-o com outros modelos Stable Diffusion 1.5, veja a pontuação de calor para acompanhar a tendência e abra-o no PirateDiffusion ou BitVector para experimentar.
Navegar por família de modelos
Ver todos os modelos