AI TIPS #7: Your AI Can Spell. You Just Have to Ask Right.
Quick takeaway: if your AI image has wrong spelling, fix the prompt first.
I tested a cheap model [Z Image]. Same settings, two prompts.
Loose prompt: "Chrysanthuum" and fake words.
Template prompt: clean text.
It did not work every time. 2 of 5 tries were clean.
Strong models like GPT Image 2.5 made fewer mistakes even with a loose prompt.
Loose prompt (before):
make a cool poster for a jazz night that says Chrysanthemum Philharmonic Rendezvous, saturday at the old warehouse, with a saxophone player and neon lights
Template prompt (after):
Poster for a jazz night, a saxophone player on a dark stage with pink and blue neon lights.
Text: "CHRYSANTHEMUM" in bold sans-serif, white, top center, large.
Text: "PHILHARMONIC RENDEZVOUS" in bold sans-serif, pink, under the first line, medium.
Text: "SATURDAY" in bold sans-serif, white, bottom center, small.
Spelling: C-H-R-Y-S-A-N-T-H-E-M-U-M P-H-I-L-H-A-R-M-O-N-I-C R-E-N-D-E-Z-V-O-U-S S-A-T-U-R-D-A-Y
Show each text once. No other text, no logos, no price tags.
Tips to remember
- Keep text short. One headline is easier than a full paragraph
- Put the exact words in quotes
- Spell names and rare words letter by letter
- Say "no other text" or the model may add its own
- Small text needs Quality [Medium] or [High]
- One wrong letter? Do an edit: "change only the word X to Y, keep everything else the same". Do not start over
Opinion:
If the image is a start frame for a video, I leave the text out.
I add text in my editor at the end.
If you have a better way to get clean text please leave a comment.
3
1
274
[Grok imagine High Quality (SOTA)] is being retired by xAI November 2nd.
This means platforms like Venice AI will also lose access to it.
This is a shame because it is the best model to build an original character from with the best realism.
The replacement Grok 2.0 is extremely nerfed in quality and barely useable for text-to-image creations.
You have 5 days left to make use of it on Venice before it’s gone. 😭
2
503
Viral French Influencer Video?
Same swap technique with WAN 3.0
🤖 Made with AI
Quick Tutorial: Character Swaps in Video
I'm creating this in response to Higgsfield's intense marketing on their "Viral AI Influencer" campaign.
Here I'm referencing a video from [audreyfrog33] on TikTok, please follow them
Quick takeaway:
- You don't need Genjutsu
- You don't need Seedance 2.5
- You don't need Higgsfield
All you need to is an understanding of the tools
I created this with WAN 3.0 because it was blocked by Seedance 2.5
Required Items:
- Character Sheet
- Video Reference
Character Sheet Prompt
-----------------------------------------------
professional photo character sheet in flat gray background #7B7B7C, left side as an extreme close up of the subjects face, right side is front and back view from head to toe.
Subject is: [ Japanese woman in her early 20's, long straight purple fading hair, arm tattoos, boss suit sleeves rolled up, gloves ]
-----------------------------------------------
Tutorial:
- Find a video to use for character swap
- Video must be less than 15 seconds
- Load the video into WAN 3.0 as a reference
- Load your character sheet into WAN 3.0 as a reference
- Set duration for 15 seconds or exact duration of video
- Set Aspect Ratio to match (9:16)
- Set output to 480p (use higher if you wish)
- Add prompt and create
Video Prompt:
[START PROMPT]
---------------------------
GLOBAL STYLE
Photoreal 30-second clip, 16:9. Same grade, lighting, and lens as the source video. Adults 21+ only. No text, no logos, no character-sheet grid.
SCENE
Replace the person in the source video with the woman from the character sheet. Keep her action, timing, and path. Do not keep the original face, hair, body, or clothes.
REFERENCE ROLES
@Video1 = motion path, timing, camera, and location ONLY. Do not copy the original person's face, hair, body, wardrobe, or identity.
@Image1 = character-sheet woman, face + body + wardrobe ONLY. Do not copy the sheet layout, turnaround poses, labels, crop, or background.
CHARACTERS
Woman, 21+, identity locked to @Image1: same face, hair, skin, proportions, and outfit from the sheet in every frame. One person only. No extra limbs, no face morph, no blend with the original actor.
LOCATION
Same room, props, and background as @Video1. Do not import the sheet backdrop.
FIRST FRAME AND BLOCKING
Frame 1 already in motion, matching the source action. She is fully the sheet character from the first frame, not a fade or morph.
SHOTS
[0-30s] She performs the same action and blocking as the person in @Video1. Camera matches the source. Identity stays locked to @Image1. Last 3 seconds hold the finished pose.
OPTICS
Match the source lens and depth of field. No beauty filter.
CAMERA
Follow @Video1 camera path only. Do not restage.
PHYSICS
Weight, cloth, and hair match her real motion. No sliding feet, no rubber limbs.
LIGHTING
Match the source practicals and shadows. Her face takes the same light direction as the original person.
AUDIO
<same diegetic room and movement SFX as the source>
no music, no score, no subtitles, no on-screen text
CONSTRAINTS
Do not copy the original person's identity. Do not paste the character sheet as a picture-in-picture or grid. Do not change the action. Faces stay on-model. No text.
-------------------------------------------------
[END PROMPT]
Here's the video on the character swap
The second video is a 14-second video clip where I want to swap the character.
The image is the character sheet I created
The last video is the result where the character is swapped.
The prompt:
-------------------------------
GLOBAL STYLE
Photoreal 30-second clip, 16:9. Same grade, lighting, and lens as the source video. Adults 21+ only. No text, no logos, no character-sheet grid.
SCENE
Replace the person in the source video with the woman from the character sheet. Keep her action, timing, and path. Do not keep the original face, hair, body, or clothes.
REFERENCE ROLES
@Video1 = motion path, timing, camera, and location ONLY. Do not copy the original person's face, hair, body, wardrobe, or identity.
@Image1 = character-sheet woman, face + body + wardrobe ONLY. Do not copy the sheet layout, turnaround poses, labels, crop, or background.
CHARACTERS
Woman, 21+, identity locked to @Image1: same face, hair, skin, proportions, and outfit from the sheet in every frame. One person only. No extra limbs, no face morph, no blend with the original actor.
LOCATION
Same room, props, and background as @Video1. Do not import the sheet backdrop.
FIRST FRAME AND BLOCKING
Frame 1 already in motion, matching the source action. She is fully the sheet character from the first frame, not a fade or morph.
SHOTS
[0-30s] She performs the same action and blocking as the person in @Video1. Camera matches the source. Identity stays locked to @Image1. Last 3 seconds hold the finished pose.
OPTICS
Match the source lens and depth of field. No beauty filter.
CAMERA
Follow @Video1 camera path only. Do not restage.
PHYSICS
Weight, cloth, and hair match her real motion. No sliding feet, no rubber limbs.
LIGHTING
Match the source practicals and shadows. Her face takes the same light direction as the original person.
AUDIO
<same diegetic room and movement SFX as the source>
no music, no score, no subtitles, no on-screen text
CONSTRAINTS
Do not copy the original person's identity. Do not paste the character sheet as a picture-in-picture or grid. Do not change the action. Faces stay on-model. No text.
----------------------------------------
1
1
350
Replying to @Bigbackhych
First of all this is how you make a character sheet.
Creating a character sheet is taking an image and creating a character sheet to act as a master image, the character sheet shows the character in high quality from multiple angles so that the model can reference it from all sides so it doesn't have to guess.
In this example I'm in Venice in Studio
-Create an image with the model [Grok Image High Quality (SOTA)]
-Edit an image with [Seedream V5 Pro]
Prompt for character sheet in Edit:
------------------------------------
professional photo character sheet in flat gray background #7B7B7C, left side as an extreme close up of the subjects face, right side is front and back view from head to toe.
------------------------------------
You will use that character sheet in your video
1
168
Replying to @clyve2022
I don't do product videos so I can't really speak for blending there.
This is a quick comparison on WAN / Seedance with two similar variations of "PILK"
Prompt:
GLOBAL STYLE
30 seconds, 16:9, photoreal premium beverage commercial. Large-format cinema, fine grain, razor product fidelity, beauty-key lighting, slow deliberate motion. Adult woman only, 21+. No cartoon, no anime, no morphing products.
SCENE
A studio product film. One woman tastes two distinct PILK cans and presents both. She holds each can, drinks from each can, then holds both together. The two packages never swap graphics.
REFERENCE ROLES
@Image1 = the woman only: face, violet hair with blunt bangs, purple-gray eyes, neck rose tattoos, forearm tattoos, hoop earrings, charcoal pinstripe suit, white shirt, black leather gloves, black heels. Do not copy the turnaround layout, gray backdrop, or standing pose.
@Image2 = Limited Edition PILK can only: blue-purple metallic body, Pepsi globe at the top, dripping purple PILK wordmark with cream outline, “Pepsi & Milk,” swirled purple-white glass graphic, “NEW FLAVOR / Limited Edition / Carbonated Milk Drink / 12 FL OZ (355mL).” Do not copy the plate, sky, or milk splashes around it. Do not restyle it into the blue condensation can.
@Image3 = Classic PILK can only: wet blue body with condensation beads, Pepsi globe, lowercase “pepsi,” bold white PILK, “Pepsi & Milk,” white milk-splash graphic on the lower third, “NET 12 FL OZ (355 mL),” silver top. Do not copy the glasses or ice. Do not restyle it into the purple dripping can.
CHARACTERS
Woman, 21+, East Asian, long straight violet hair, blunt bangs, neutral composed mouth, beauty marks, neck roses, tattooed forearms, black gloves, pinstripe suit, heels. Same face and wardrobe in every shot.
LOCATION
Seamless cool-gray cyclorama, low reflective acrylic table, soft cream floor bounce. No kitchen, no street, no extra props except the two cans and a clear glass already on the table.
FIRST FRAME AND BLOCKING
Already in motion. Medium-wide. She stands behind the table, gloved hands raising both cans to chest height, Limited Edition can in her right hand, Classic can in her left. Labels face camera. Hair shifts once.
SHOTS
0–5s: Slow push-in. Both cans readable side by side. Limited Edition keeps the dripping purple PILK and swirl-glass art. Classic keeps condensation, white PILK, and the milk-splash band. She turns each can a quarter turn so the wordmarks catch light.
5–11s: She sets the Classic can down. Macro on the Limited Edition can in her right glove, then she brings it to her mouth and drinks. One swallow, throat moves, can stays the purple graphic can. She lowers it; a thin milk-soda line on her lip.
11–17s: She lifts the Classic can with her left glove. Condensation beads stay on the blue metal. She drinks from this can. Different sip, smaller, then a quiet exhale. Label never changes to the purple wordmark.
17–23s: Insert tabletop hero. Both cans standing, then her gloved hands enter and pick them up again. Limited Edition right, Classic left. No logo blend, no extra can, no third design.
23–30s: Beauty close. She holds both cans beside her face, labels square to lens, and takes a last small sip from the Limited Edition can while the Classic can stays in frame. Hold. Eyes on camera.
OPTICS
50mm for the woman, 90mm macro for can labels. Shallow depth, labels sharp, background falloff. No lens flare streaks across the wordmarks.
CAMERA
Locked commercial moves only: slow push, one motivated cut to macro, one return to beauty. No handheld, no whip pans.
PHYSICS
Real aluminum weight in the gloves. Liquid shifts inside each can on the tilt. Condensation only on the Classic can. No liquid leaking through metal. Hair and suit cloth move only from her turn.
LIGHTING
Big soft key from frame-left, thin rim on hair and can shoulders, white bounce in the table. Cool commercial grade, skin natural, metal speculars controlled.
AUDIO
<soft glove on aluminum, can lift, two distinct swallows, one quiet exhale, studio room tone>
{no spoken line}
(light polished commercial bed, sparse, under the sips — no lyrics)
no subtitles, no generated on-screen text beyond the print already on the cans
CONSTRAINTS
Two cans only, identities locked for all 30 seconds. Limited Edition always matches @Image2. Classic always matches @Image3. Never merge wordmarks, never swap colors, never duplicate a third can. Woman matches @Image1 in every shot. No identity drift, no warped labels, no extra fingers, no logo invention.
🤖 Made with AI
3
1,510
Quick Tutorial: Character Swaps in Video
I'm creating this in response to Higgsfield's intense marketing on their "Viral AI Influencer" campaign.
Here I'm referencing a video from [audreyfrog33] on TikTok, please follow them
Quick takeaway:
- You don't need Genjutsu
- You don't need Seedance 2.5
- You don't need Higgsfield
All you need to is an understanding of the tools
I created this with WAN 3.0 because it was blocked by Seedance 2.5
Required Items:
- Character Sheet
- Video Reference
Character Sheet Prompt
-----------------------------------------------
professional photo character sheet in flat gray background #7B7B7C, left side as an extreme close up of the subjects face, right side is front and back view from head to toe.
Subject is: [ Japanese woman in her early 20's, long straight purple fading hair, arm tattoos, boss suit sleeves rolled up, gloves ]
-----------------------------------------------
Tutorial:
- Find a video to use for character swap
- Video must be less than 15 seconds
- Load the video into WAN 3.0 as a reference
- Load your character sheet into WAN 3.0 as a reference
- Set duration for 15 seconds or exact duration of video
- Set Aspect Ratio to match (9:16)
- Set output to 480p (use higher if you wish)
- Add prompt and create
Video Prompt:
[START PROMPT]
---------------------------
GLOBAL STYLE
Photoreal 30-second clip, 16:9. Same grade, lighting, and lens as the source video. Adults 21+ only. No text, no logos, no character-sheet grid.
SCENE
Replace the person in the source video with the woman from the character sheet. Keep her action, timing, and path. Do not keep the original face, hair, body, or clothes.
REFERENCE ROLES
@Video1 = motion path, timing, camera, and location ONLY. Do not copy the original person's face, hair, body, wardrobe, or identity.
@Image1 = character-sheet woman, face + body + wardrobe ONLY. Do not copy the sheet layout, turnaround poses, labels, crop, or background.
CHARACTERS
Woman, 21+, identity locked to @Image1: same face, hair, skin, proportions, and outfit from the sheet in every frame. One person only. No extra limbs, no face morph, no blend with the original actor.
LOCATION
Same room, props, and background as @Video1. Do not import the sheet backdrop.
FIRST FRAME AND BLOCKING
Frame 1 already in motion, matching the source action. She is fully the sheet character from the first frame, not a fade or morph.
SHOTS
[0-30s] She performs the same action and blocking as the person in @Video1. Camera matches the source. Identity stays locked to @Image1. Last 3 seconds hold the finished pose.
OPTICS
Match the source lens and depth of field. No beauty filter.
CAMERA
Follow @Video1 camera path only. Do not restage.
PHYSICS
Weight, cloth, and hair match her real motion. No sliding feet, no rubber limbs.
LIGHTING
Match the source practicals and shadows. Her face takes the same light direction as the original person.
AUDIO
<same diegetic room and movement SFX as the source>
no music, no score, no subtitles, no on-screen text
CONSTRAINTS
Do not copy the original person's identity. Do not paste the character sheet as a picture-in-picture or grid. Do not change the action. Faces stay on-model. No text.
-------------------------------------------------
[END PROMPT]
🤖 Made with AI
I wanted to see how WAN 3.0 handles TikTok style dance performances.
The first video I hand wrote the prompt, two videos that I took to TikTok to dub the original music.
The second video I used a skill I created for Grok to optimize it.
- Video Model: [WAN 3.0 Reference]
- Image Model: [Grok Imagine High Quality (SOTA)]
- Image Edit Model: [Seedream V5 Pro]
- WAN 3.0 Skill: grok.com/skill-link/38992646…
- Platform: Venice.ai
- Referral Link: venice.ai/chat?ref=4glZT-
Prompts in comments
Original Inspiration Post xitter.cf/LoveUolanda/status/209…
🤖 Made with AI
调试了9个版本终于稳定下来了。
这种网红视角的短视频在h3模式使用图生视频来完成 对提示词要求非常高。
还踩了个坑 .
H3 在高像素模式下,模型会优先追求人脸细节还原;俯拍 45‑55° 向下拍摄,人脸会产生透视形变(额头大、下巴收)。模型内部有隐性偏好:高清晰度生成时尽量避免人脸强烈透视畸变,主动把相机拉回眼平,保证人脸 “好看端正”,直接无视你的机位硬约束。
也在文章分享了修复方案。
提示词 xitter.cf/LoveUolanda/status/209…
芙宁娜|时装走秀 💙🎭✨
芙宁娜登上属于她的时尚舞台。
随着灯光与音乐展开,优雅、戏剧感与舞台气场交织在一起,属于水之国的时装秀正式开始。
从舞台中央走来,每一步都像一场属于芙宁娜的精彩演出。✨
今天的主角,当然是芙宁娜。
喜欢这场走秀的话,点赞❤️收藏⭐关注🔔支持一下!
推荐 X 标签:
#芙宁娜 #Furina #原神 #GenshinImpact #时装走秀 #FashionShow
#フリーナ #原神 #ファッションショー
#NguyenThan #GenshinImpactVN #NhanVatGame
#AIArt #AIVideo #提示词分析 #promptshare #MINIMAXH3 #ai教程
WARNING ABOUT GROK AUTO TOP-UP
If you disabled it before you need to disable it again.
They made a change and enabled it by default again.
The new setting charges you if your balance of extra credit goes below a 3 dollar threshold. I was charged 5 dollars without any desire or consent on the setting.
This is predatory design
- The inability to remove payment method from top up unrelated to account sub.
- Enabling auto top up without user consent/warning
- Enabling auto top up again after previously disabling it













