Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is available for use and will generate similar character to the ones seen in the images.

Model Description by Creator

NOTE: Read comment attached to each sample to see the full prompt. These are generated in two steps with different prompts.

Since purchasing a few Afremov paintings about 10 years ago, the studio has emailed me thousands of paintings, almost daily. I decided to make a LoRA out of a selection of these.

The artist sadly died in 2019, but has a very recognizable vibrant impasto style. Often with trees, street lamps, wet streets, night cities - but also music, dancers, animals, seascapes.

Note, samples were made during testing and contain the extended development LoRA name, the final released LoRA name is <afrem0vSD15v1>

I used this LoRA training guide & yaml here: https://civitai.com/models/52697/tutorial-konyconi-style-lora

  • Trained against SD1.5 base model with kohya_ss Dreambooth LoRA at 76 paintings with signatures removed.

  • I classified 44 of the paintings as 'afrem0vDabbs' and 32 'afrem0vStrokes' after the two basic brush styles the artist favors. These triggers, together with LoRA strength are the primary variable controls you have in the prompts.

  • WD14 Tags (SmilingWolf/wd-v1-5convnextv2-tagger-v2) were cleaned up using BooruDatasetTagManager

  • Followed konyconi training guide except:

  • -- Increased repeats/repetitions (not epochs) from 10 to 15. Tested 10,15,20 repeats and 15 worked best here.

  • -- Increased resolution from 512x512 to 768x768 which gave distinctly better results.

  • -- Decreased Training Batch Size from 4 to 1 (especially for 768x768) because 8Gb VRAM limitations. There is some indication that batch size 1 supports better results anyway.

Don't expect great faces, especially middle to far distance. The style is 'rough' by nature.

Upscaled with ControtNet 1.1.183 tile_resample and Ultimate SD upscale (x2). Upscale prompt focuses on the oil painting aspect rather than the subject:

<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), thick oil painting, dramatic lighting, (brush strokes:1.6) <lora:add_detail:1.4>

Negative prompt: text, writing, words, signature

Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 6, Seed: 518656980, Size: 1536x1024, Model: revAnimated_v11, Denoising strength: 0.24, Ultimate SD upscale upscaler: R-ESRGAN 4x+, Ultimate SD upscale tile_width: 512, Ultimate SD upscale tile_height: 512, Ultimate SD upscale mask_blur: 8, Ultimate SD upscale padding: 32, ControlNet 0: "preprocessor: tile_resample, model: control_v11f1e_sd15_tile [a371b31b], weight: 1, starting/ending: (0, 1), resize mode: Crop and Resize, pixel perfect: False, control mode: Balanced, preprocessor params: (64, 1, 64)"

Add Detail LoRA used during upscale:

https://civitai.com/models/58390/detail-tweaker-lora-lora

Sample prompts (the upscaler strips these unfortunately):

a painting of a person holding an umbrella, big beautiful street lamp, dripping colors, mystical feeling, autumn garden, obscured hooded person walking, splash painting, surreal dreamy poetic, street lamp <lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, afremov

Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 1336031228, Size: 768x512, Model: revAnimated_v11

a painting of a couple walking their dog in the park, colorful oil painting, vibrant landscape painting, man and woman walking together, romanticism landscape painting, canvas art print, bright depth oil colors, impressionist oil painting <lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, afremov

Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2495249670, Size: 768x512, Model: revAnimated_v11

a portrait painting of Audrey Hepburn, black and white oil painting, romanticism, canvas art print, bright depth oil colors, impressionist oil painting <lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, afremov Negative prompt: signature

Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 1791437548, Size: 512x768, Model: revAnimated_v11

a portrait painting of Audrey Hepburn, black and white oil painting, romanticism, canvas art print, bright depth oil colors, impressionist oil painting <lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, afremov Negative prompt: signature

Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2082324723, Size: 512x768, Model: revAnimated_v11

a painting of many colorful hot air balloons, hot air balloons, vibrant oil painting, bright depth oil colors, high detailed oil painting, impressionist oil painting <lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, afremov

Negative prompt: signature

Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 1866081365, Size: 512x768, Model: revAnimated_v11

a painting of the roman coliseum, vibrant oil painting, bright depth oil colors, high detailed oil painting, impressionist oil painting <lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, afremov

Negative prompt: signature, person

Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2646698015, Size: 768x512, Model: revAnimated_v11

a painting of the french alps in winter, white snow covered mountains, ski, bright depth oil colors, high detailed oil painting, impressionist oil painting <lora:afrem0v-000013-768x768x15:0.75>, afrem0vStrokes:1.1, afremov

Negative prompt: signature, person

Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2587525543, Size: 768x512, Model: revAnimated_v11

a green vintage race car, wet street, night, bright depth oil colors, high detailed oil painting, impressionist oil painting <lora:afrem0v-000013-768x768x15:0.75>, afrem0vStrokes:1.1, afremov

Negative prompt: signature, person

Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 3711991308, Size: 768x512, Model: revAnimated_v11

a content chamber maid illuminated by candle light, detailed Rembrandt face, night, bright depth oil colors, high detailed oil painting, impressionist oil painting <lora:afrem0v-000013-768x768x15:0.75>, afrem0vStrokes:1.1, afremov

Negative prompt: signature, person, anime

Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2763075539, Size: 512x768, Model: revAnimated_v11

African american violin player, country music, barn, detailed Rembrandt face, night, bright depth oil colors, high detailed oil painting, impressionist oil painting <lora:afrem0v-000013-768x768x15:0.75>, afrem0vStrokes:1.1, afremov

Negative prompt: signature, person, anime

Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 1649546032, Size: 512x768, Model: revAnimated_v11, Variation seed: 2801926985, Variation seed strength: 0.29

a tropical beach, pineapple, bright depth oil colors, high detailed oil painting, impressionist oil painting <lora:afrem0v-000013-768x768x15:0.75>, afrem0vStrokes:1.1, afremov

Negative prompt: signature

Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2164287770, Size: 768x512, Model: revAnimated_v11, Variation seed: 696583036, Variation seed strength: 0.29

Images Generated With This Model

<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), thick oil painting, dramatic lighting, (brush strokes:1.6) <lora:add_detail:1.4>
N/A
Hidden For Public Users
<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), thick oil painting, dramatic lighting, (brush strokes:1.6) <lora:add_detail:1.4>
<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), thick oil painting, dramatic lighting, (brush strokes:1.6) <lora:add_detail:1.5>
N/A
Hidden For Public Users
<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), thick oil painting, dramatic lighting, (brush strokes:1.6) <lora:add_detail:1.5>
<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), thick oil painting, dramatic lighting, (brush strokes:1.6) <lora:add_detail:1.4>
N/A
Hidden For Public Users
<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), thick oil painting, dramatic lighting, (brush strokes:1.6) <lora:add_detail:1.4>
<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), thick oil painting, dramatic lighting, (brush strokes:1.6) <lora:add_detail:1.4>
N/A
Hidden For Public Users
<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), thick oil painting, dramatic lighting, (brush strokes:1.6) <lora:add_detail:1.4>
<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), oil painting, dramatic lighting, (brush strokes:1.2) <lora:add_detail:1.7>
N/A
Hidden For Public Users
<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), oil painting, dramatic lighting, (brush strokes:1.2) <lora:add_detail:1.7>
<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), thick oil painting, dramatic lighting, (brush strokes:1.6) <lora:add_detail:1.4>
N/A
Hidden For Public Users
<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), thick oil painting, dramatic lighting, (brush strokes:1.6) <lora:add_detail:1.4>
<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), thick oil painting, dramatic lighting, (brush strokes:1.6) <lora:add_detail:1.4>
N/A
Hidden For Public Users
<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), thick oil painting, dramatic lighting, (brush strokes:1.6) <lora:add_detail:1.4>
<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), thick oil painting, dramatic lighting, (brush strokes:1.6) <lora:add_detail:1.4>
N/A
Hidden For Public Users
<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), thick oil painting, dramatic lighting, (brush strokes:1.6) <lora:add_detail:1.4>
<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), thick oil painting, dramatic lighting, (brush strokes:1.6) <lora:add_detail:1.4>
N/A
Hidden For Public Users
<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), thick oil painting, dramatic lighting, (brush strokes:1.6) <lora:add_detail:1.4>
<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), thick oil painting, dramatic lighting, (brush strokes:1.6) <lora:add_detail:1.5>
N/A
Hidden For Public Users
<lora:afrem0v-000013-768x768x15:0.75>, afrem0vDabbs:1.1, thick (impasto:1.2), thick oil painting, dramatic lighting, (brush strokes:1.6) <lora:add_detail:1.5>

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Your All-in-One AI Image Solution

AIEasyImage brings AI image technology to everyone. Create stunning visuals, edit like a pro, and develop your unique style – all with the power of AI. No technical skills required!