KFT Requiem Fur a Dream [Illustrious Semi-Real Checkpoint] - v3VAE
Palavras-chave e Tags Relacionadas
Prompts Recomendados
kftenhance, masterpiece, best quality, amazing quality, realistic
Prompts Negativos Recomendados
bad quality, worst quality, worst detail, sketch, censor, simple background, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, artistic error, username, scan
Parâmetros Recomendados
samplers
steps
cfg
Dicas
Works best combined with KFT Furropean Extreme (Illustrious) LORA at low weights (0.2 - 0.6) for the full KFT FE² experience.
Use checkpoint + LORA combination for optimal style with LORA strengths of 0.1-0.3.
Avoid using Euler A sampler as it yields worse fur quality.
Hi res fix is recommended for better results.
Destaques da Versão
05/02/25 - v3VAE: Further merging with 20% new realism checkpoints and additional refinements with Furropean datasets.
Works best combined with Furropean Extreme at low strength (0.1 - 0.4) to keep style with proper prompt adherence of checkpoint.
05/02/25: v3! 🐯 As part of the lead-up to my Civitai account birthday, I figured it's a good time to get weird with a RFaD update.
Celebrating my 200th model posted to Civitai by going back to the first model roots with a realism/semi-realism furry focused Illustrious checkpoint merge from a family friendly name you can trust for your furry/scaly/feathery needs.
Recommended positive tags (beginning of prompts):
masterpiece, best quality, amazing quality, very aesthetic, high resolution, absurdres, newest, photorealism, realistic,
Recommended negative tags:
3d, anime, 2d, bad quality, worst quality, worst detail, sketch, censor, simple background, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early,chromatic aberration, signature,artistic error, username, scan
Works best in combination with KFT Furropean Extreme (Illustrious) at low weights (0.2 - 0.6).
That way you get the full KFT FE² experience!
Gallery images show examples using Checkpoint + LORA as I feel the combination of the two is where the sweet style spot is (strengths of 0.1-0.3).
Recommended settings:
Sampler: DPM++ 2M Karras / DPM++ 3M Karras (GPU seeded) or SGM Uniform
(Euler A gives much worse fur quality with most tested checkpoints)
Steps: 25+
Extras:
Hi res fix recommended!
As mentioned before, recommend using this checkpoint in combination with KFT Furropean Extreme (at low weights: 0.2 - 0.5)
Detalhes do Modelo
Tipo de modelo
Modelo base
Versão do modelo
Hash do modelo
Palavras treinadas
Criador
Discussão
Por favor, faça log in para deixar um comentário.