Loaded
Download
1 variant available
bf16 SafeTensor
betty_rubble_mmh3_minimaxh3_e10.safetensors
BF16, good balance • 295.8 MB
Verified: 20 hours ago
24
287
6.2K
Generation, training and LoRA distribution on Civitai are covered by Civitai’s own license agreement with MiniMax. If you download these weights and run them yourself, your use is instead governed by the MiniMax H3 Community License Agreement, whose grant excludes the European Union, the United Kingdom, the Republic of Korea and the United States of America.
MiniMax H3
Mini Max H3: 0.8
subject_definitions: <Subject 1> (S1) a female, Betty Rubble is the primary character in the video. (S1) is a mature 25-year-old American woman with a high pitched sweet voice with a strong New York City accent of the 1960s.
retention_analysis: <Subject 1> (appears in [Shot 1]): fully_preserved - She has dark black hair styled in a short, voluminous bob with bangs and a blue hair bow, light brown eyes, and medium skin tone. She wears a solid light blue halter style dress with a black neckstrap that joins at a white scallop shell pendant and has a jagged hemline.Krea2: Recommended Strength: 0.75-0.85
betty rubble, she has dark black hair styled in a short, voluminous bob with bangs and a blue hair bow, light brown eyes, and medium skin tone.She wears a solid light blue halter style dress with a black neckstrap that joins at a white shell pendant and has a jagged hemline.
My final dataset of 56 images, I used these to train this model: "Betty Rubble - Realistic (ToonToLife) - The Flintstones (1960)" who is canonically in her mid 20s to 30yo. This specific version is trained at ~2,500 steps. I recommend using at 0.8 strength. Because the source material is a highly stylized 2D cartoon, the measure of success and interpretation of a "realistic" counterpart is inherently subjective. I welcome your feedback and test images!
This LoRA is an experiment in translating a 2D animated style into photorealism. I used a combination of custom cartoon-style character LoRAs at low weights (0.3–0.5 strength) alongside detailed prompting and other style LoRAs to push the outputs toward realism. From these, I selected the best 20–60 images to train an initial realistic LoRA. Then, as needed, I generated a new batch of images and selected those that most closely matched the target body shape and consistent facial features to train the final LoRA.