This week I try to generating each shot with styleframe, character sheets and environment references.
Style prompts for every shot.
Result
Problems: have some inconsistancy problems. The scene and the bottle don’t match.
The first two shots were generated as one sequence, and they did not have the same consistency problems. The background, lighting, and overall visual style stayed much more stable between the shots.
This suggests that, for shots where the environment is clearly visible, it may be better to group them into one continuous sequence and generate them together. This gives the AI more context about the location and helps it keep the background design more consistent.
However, this method also requires a clearer storyboard and a more detailed prompt. The timing, camera movement, character actions, and transitions between shots all need to be planned in advance.
Originally, we use Chinese for environment generation. But during experiment, there appear to be some inaccuracy. I wonder if it has somthing to do with language.
After research, it appears language will affact the model to some extent.
Language and Prompting in Image Generation
Language can influence image results. Even if two prompts have the same meaning, different languages may lead to slightly different styles, details, or levels of accuracy.
English style keywords are often more stable. Many image models respond well to common English visual terms such as painterly brushstrokes, hand-painted texture, low saturation, and dusty atmosphere.
Chinese is still very useful. Chinese can express mood, intention, and subtle creative ideas clearly, especially if the user is more comfortable writing in Chinese.
Direct translation is not always enough. A word like “笔触感” can mean brushstroke texture, painterly texture, or rough brushwork, and each may produce a different result.
A mixed-language workflow works best. The user can first describe the idea in Chinese, then refine the prompt with specific English visual keywords.
Overall, prompting is about clarification. The goal is not just to translate, but to turn creative ideas into clear visual instructions that the model can follow.
Turtle: The diagonal feet move almost simultaneously, with the front feet slightly faster than the hind feet. The head stays mostly still, held up, only turning to look in the desired direction. The tail also remains largely still. The front feet move first; the hind feet barely leave the ground and quickly follow. The lower body stays close to the ground, propped up by the front feet. When swimming, it relies mainly on the front feet for paddling; the hind feet seem to only participate in turning. The larger the turtle, the slower its movements.
Lizard & Crocodile: (this seems to be the main focus) The diagonal feet move almost simultaneously, with little noticeable difference between front and hind feet — though the hind feet might lift just a tiny fraction slower. The body twists with a wide range of motion, forming an S-shape. The tail acts as a huge follow-through. They can stand up and run — it looks hilarious, with their legs swinging in circles. It feels like the wild running seen in cartoons was modeled after lizards. This could probably fill its own page. The smaller the body, the faster the movement.
Crocodile swimming: It mainly propels itself forward with its tail; the limbs stay mostly still, only moving when turning or grabbing onto something.
Crocodile running: It’s actually quite similar to a leopard — a fast forward leap.
Snake: Undulatory movement — they send a wave down their body and move forward.
Pre-structure notes:
Group turtle, lizard, and crocodile together — cover walking, running, and swimming separately
Snake as a separate section — maybe divide into movement and stillness?
Should we add some more cartoonish, animated-style performance or keep it completely realistic?
Creature animation in general
Animal Leg Types
Plantigrade – The whole foot (sole) touches the ground. Examples: humans, bears, rabbits, raccoons, kangaroos, etc.
Digitigrade – Only the toes touch the ground; the heel is lifted. Examples: cats, dogs, birds, dinosaurs, etc.
Unguligrade – Only the tips of the hooves touch the ground. Examples: horses, cows, deer, and other hoofed animals.
Structural Differences Between Herbivores and Carnivores
Body shape
Herbivore: huge rib cage, heavy body
Carnivore: slim, agile body
Spine
Herbivore: rigid
Carnivore: flexible
Main function
Herbivore: store food
Carnivore: hunt
Gait Study
Using the Icelandic horse as an example, demonstrating 5 gaits.
Emphasize observing the spine curve in side view and top view.
The spine curve affects the movement relationship between the chest, hips, and head.
Anatomy Key Points
The structure of the scapula (shoulder blade) and wings is crucial for flight or forelimb movement.
Anatomy study should serve animation performance, not pure medical anatomy.
For image gerneration, the most popular three AI are image-2, nano bananas and midjourney
Midjourney:
The pictures it generates are more aesthetically pleasing, with better color schemes and lighting effects. However, it is very difficult to modify and control the picture. Greater freedom is needed for it to generate better pictures. A good thing is that it can easily
Image2 & nano bananas
Both of these models will be more rigorous and easier to modify. In comparison, the image generated by “image2” will look more attractive.
