Create

9527 Detail Realistic XL

CHECKPOINT
Original


Updated:

blur image
masterpiece, best quality, analogue photo of adult girl in sweater and sweater hat, looking at viewer, long hair,head shot, hold cheeks with hands, close up face, extremely beautiful detailed face, medium breasts, (cute face, temptations look), snowing, snowing background, high key lighting, eye level, Leica M3, Ektar 100, 50mm, (vignette photography), (professional photo, balanced photo, balanced exposure)
  • masterpiece, best quality, analogue photo of adult girl in sweater and sweater hat, looking at viewer, long hair,head shot, hold cheeks with hands, close up face, extremely beautiful detailed face, medium breasts, (cute face, temptations look), snowing, snowing background, high key lighting, eye level, Leica M3, Ektar 100, 50mm, (vignette photography), (professional photo, balanced photo, balanced exposure)
  • (masterpiece, best-quality, 8k, hdr, film grain), photo of Japanese girl in white cardigan, extreme detailed face, skinny face, triangle face shape, flowing long hair, (close up portrait), soft bokeh, hard shadows, simple background, white background, (instagram photo), masterpiece, best quality, analogue photo of 1girl, extremely beautiful detailed face, best shadow, medium breasts, white shirt, simple background
  • masterpiece, best quality, 1girl, mecha suit,  menpo, upper body, underboob, portrait, white orange armor, blonde shimmering hair, 8K, RAW, best quality, masterpiece, ultra high res, colorful, (medium wide shot), (dynamic perspective), sharp focus , (depth of field, bokeh:1.3), extremely detailed eyes and face, beautiful detailed eyes,large breasts,black gold, trimmed gear,In a futuristic weapons factory, masterpiece, best quality, analogue photo of 1girl, extremely beautiful detailed face, best shadow, medium breasts, white shirt, simple background
  • Cyberpunk, sci-fi, dark-fantasy, portrait photo of a cat cyborg robot in a chemical laboratory, volumetric lighting, highly detailed,
  • Cyberpunk, sci-fi, dark-fantasy, portrait photo of a war man cyborg robot in a chemical laboratory, kodak portrait 400, 8k, soft light, volumetric lighting, highly detailed, britt marling style 3/4, intricate, elegant, highly detailed, devil-armor, 2D motifs detailed dark fantasy digital painting, artstation, concept art, smooth, sharp focus, illustration,
  • (8k, RAW photo, best quality, masterpiece:1.3),(realistic, photo-realistic:1.37), cute asian girl, solo, (beautiful eyes:1.2), perfect face, (cowboy shot:1.2), ((bubble bath)), ((soap bubbles)) , bathing, bubble cover whole body masterpiece, best quality, analogue photo of 1girl, extremely beautiful detailed face, best shadow, medium breasts, white shirt, simple background

v1, v1-delta, v2 版本的模型對於 DPM++ 2M SDE 採樣器會有異常狀況,請不要使用這個採樣器。

推薦使用 DPM++ 3M 系列採樣器。

v1, v1-delta, v2 versions of the model will have an exception condition for the DPM++ 2M SDE sampler, please do not use this sampler.

The DPM++ 3M series sampler is recommended.

v1、v1-delta、v2 バージョンのモデルには、DPM++ 2M SDEサンプラーの例外条件がありますので、このサンプラーは使用しないでください。

サンプラーはDPM++ 3Mシリーズを推奨。

v1, v1-delta, v2 버전의 모델에는 DPM++ 2M SDE 샘플러에 대한 예외 조건이 있으므로 이 샘플러를 사용하지 마세요.

DPM++ 3M 시리즈 샘플러를 권장합니다.

555
Runs
0
Downloads
Uploaded
Base ModelSDXL 1.0
CLIP SKIP 推薦使用 1。 CLIP SKIP recommends the use of 1. CLIP SKIP では 1 の使用を推奨している。 CLIP SKIP 는 1 을 사용하는 것이 좋습니다. 這是從 v4.0 與後期訓練的 SDXL Lora 模型融合而成,利用 GPT4 與 DallE3 針對 SDXL Lora 重新調整提示詞,總共使用了 12 組重新訓練的 SDXL Lora 來融合此模型。另外額外加入了以下模型,皆使用自行訓練的 Lora 進行微調: HelloWorld SDXL v6.0 這個版本由於調整了 Text Encoder 的部分,所以對於提示詞的權重相當敏感,如果無法正確產生圖片,請調整你的提示詞權重。 This is a fusion of the SDXL Lora model from v4.0 and the later trained SDXL Lora model. The cues were retuned for SDXL Lora using GPT4 and DallE3, and a total of 12 sets of retrained SDXL Lora were used to fuse this model. In addition, the following models were added and fine-tuned using self-trained Lora: HelloWorld SDXL v6.0 This version is sensitive to cue weights because it adjusts the Text Encoder part, so please adjust your cue weights if you can't generate images correctly. これはv4.0のSDXL Loraモデルと後から学習されたSDXL Loraモデルの融合である。キューはGPT4とDallE3を用いてSDXL Lora用に再チューニングされ、合計 12 セットの再トレーニングされたSDXL Loraがこのモデルの融合に使用されました。さらに、以下のモデルを追加し、自己学習したLoraを用いて微調整を行った: HelloWorld SDXL v6.0 このバージョンは、Text Encoderパートを調整するため、キューの重みに敏感です。正しく画像を生成できない場合は、キューの重みを調整してください。 이것은 v4.0의 SDXL Lora 모델과 이후 학습된 SDXL Lora 모델을 융합한 것입니다. 이 모델을 융합하기 위해 GPT4와 DallE3를 사용하여 SDXL Lora에 맞게 큐를 재조정했으며, 총 12 세트의 재트레이닝된 SDXL Lora를 사용했습니다. 또한 자체 훈련된 Lora를 사용하여 다음 모델을 추가하고 미세 조정했습니다: HelloWorld SDXL v6.0 이 버전은 텍스트 인코더 부분을 조정하기 때문에 큐 가중치에 민감하므로 이미지가 제대로 생성되지 않는 경우 큐 가중치를 조정하십시오.
  • Download the model file

  • Use without crediting

  • Share merges of this model

  • Use different permissions on merges

Commercial use: Use on generation services

Comments

Related Posts