Autoplay
Run Locally
retro_minimaxh3_3361247_epoch_10.safetensors
296 MB · SafeTensor · bf16
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
MINIMAX H3 · LoRAs
by Mayer2003 - Nostalgic Cinema - LoRA was trained on highly descriptive, cinematic, and vintage fashion data.
Creator notes
📼 The Ultimate 80s/90s LoRA Guide for z-image-turbo 📼
Let’s spice things up! LoRA was trained on highly descriptive, cinematic, and vintage fashion data. To get the best results out of z-image-turbo, you need to feed it rich, narrative-style prompts.
---
### 🎬 1. THE TRIGGER WORDS & VIBE
> The Secret Sauce: This LoRA doesn't just want a subject; it wants a scene. It thrives on paragraph-long descriptions rather than simple tag lists.
🗓️ *Eras:** 1980s, 1990s, 1980s-1990s, Early 1980s
🎞️ *Mediums:** color studio photograph, cinematic scene, television production, color film
🌫️ *Textures:** slight film grain, water droplets visible on skin, damp skin/perspiration
---
### 🧬 2. THE AESTHETIC DNA (What your LoRA loves)
| Category | 🌟 Keywords to Inject |
| :--- | :--- |
| 👗 Wardrobe | athletic wear, one-piece swimsuits, oversized blazers, festive ensembles, tall boots with fluffy cuffs |
| 💇 Hair & Makeup | wet curly hair, wavy dark brown hair, thin blue headband, natural skin tones |
| 💡 Lighting | professional studio lighting, bright lighting, natural daylight, overcast sky |
| 🎥 Camera/Framing | sharp focus, medium shot, cinematic composition, slightly soft focus |
---
### 🛠️ 3. THE MASTER FORMULA
Use this blueprint to build your prompts. Copy the block below and fill in the blanks!
```text
[Era/Decade], [Cinematic/Photo Medium]. The central figure is [Subject Description] wearing [Highly Detailed Wardrobe]. They are [Action/Pose] in [Detailed Setting/Background]. [Lighting & Camera Specs, e.g., film grain, sharp focus, natural lighting].
```
---
### 🚀 4. COPY-PASTE PROMPTS (Ready to Generate!)
🏋️♀️ The 80s Aerobics / Fitness Vibe
```text
1980s, color photograph. The central figure is a young woman with wet, curly hair wearing a red one-piece swimsuit. She is standing in a retro gym or fitness setting. Water droplets are visible on her skin, suggesting physical exertion. Professional studio lighting, sharp focus, slight film grain, natural skin tones, medium shot.
```
🕵️♂️ The 90s TV Drama / Cinematic Vibe
```text
1980s-1990s, cinematic scene featuring a young woman in an oversized beige blazer over a grey knit sweater and a man in a dark suit with a patterned tie. They are standing on the porch of a white house, looking off-camera with serious expressions. High-definition color film with sharp focus and natural lighting, typical of late 20th-century television productions.
```
🏎️ The Vintage Architecture & Auto Vibe
```text
1990s, exterior shot of a modernist residence featuring a large covered carport with concrete pillars. Under the portico sits a red convertible sports car parked next to a motorcycle. Clean lines, flat roofs, lush green trees frame the background under an overcast sky. Cinematic composition, moderate resolution color photograph, slightly soft focus, natural daylight.
```
---
### 🤫 5. PRO-TIPS FOR z-image-turbo
> ⚠️ DON'T BE LAZY WITH DETAILS!
> Notice how the training data reads like a novel? (e.g., "decorative cloud-like stitching across the chest", "large advertisement for Adidas sneakers"). The more specific and narrative your prompt is, the better the LoRA will perform!
🏷️ *Name-drop Brands & Eras:** Mentioning things like Adidas, Corvette C2, or 1994 grounds the AI and forces it into the correct historical context.
💦 *Embrace the Sweat & Grain:** Don't be afraid to use words like perspiration, damp, or film grain. It adds that authentic, gritty vintage realism!
🧍 *Pose Directives:** Use strong verbs like standing confidently, arms spread outward mid-movement, or looking off-camera with serious expressions.
Trigger words
r3tr0sks
SHA256
83CE18886426DBE60EEC89D96748A58EFD93C9C0F416C61E0BA571D4912489EC
ModelTrends.ai Model ID
#27508
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Size
544x960
Prompt
r3tr0sks,
integrated_multimodal_description: [Shot 1] 1970s Super 8 home movie aesthetic, warm golden tones with soft halation and heavy film grain, a close-up selfie-style shot frames a cute young woman in her early twenties with sun-kissed freckles, a daisy flower crown, and a flowing cream blouse, holding the camera at arm's length. The camera shakes slightly with small amplitude at slow speed as she tilts her head, tucks a strand of honey-brown hair behind her ear, and giggles directly into the lens. The warm, airy young woman with a gentle, melodic voice (S1) says: [English] Wait, is this thing actually recording? She leans closer, her nose nearly filling the frame, then bursts into laughter while the golden-hour sunlight flares across the lens.
overall_soundscape: A gentle summer breeze rustles nearby leaves while distant birds chirp softly. Her light laughter rings out, and the faint mechanical whir of a vintage film camera can be heard beneath her voice.
non_diegetic_music: A warm, lo-fi acoustic guitar melody with gentle fingerpicking, accompanied by soft tambourine shakes and the subtle crackle of aged film audio.
Settings
Sampler
LCM
Steps
10
Seed
1019906710658595
Size
1472x1088
Prompt
r3tr0sks,
integrated_multimodal_description: [Shot 1] 1980s VHS action, 16:9 format, tracking lines, neon color bleed, and a slight tape warp. A night street in Miami glows with pink and cyan neon. <Picture 2> is SpongeBob SquarePants (S2) with sunglasses leans against a black muscle car. (S1) Sandy Cheeks <Picture 1> is in an astronaut suit with a fish bowl over her head runs up, holding a hamburger. The camera tracks right with small amplitude at fast speed as she reaches him. She (S1) says in a breathless, sharp voice: [English] They're coming. We gotta move. He (S2) replies in a low, cool voice: [English] Let them come. [Shot 2] At 00:07.000, the camera cuts to a close-up of the hamburger being inserted into a car computer, green code flashing on a tiny screen. The green laser line sweeps smoothly across the surface of the hamburger, casting a vibrant, neon-glow over the sesame seed bun. As it passes, a digital readout begins to flicker into existence, breaking down the burger's composition in real-time.
overall_soundscape: Car engines idle, distant sirens wail, neon buzzes, and the floppy disk clicks into the drive.
non_diegetic_music: A driving 1980s synthwave track with gated reverb drums, pulsing bass, and a heroic synth lead.
Settings
Sampler
LCM
Steps
10
Seed
1019906710658595
Size
1472x1088
Prompt
r3tr0sks,
integrated_multimodal_description: [Shot 1] 1980s VHS action, 16:9 format, tracking lines, neon color bleed, and a slight tape warp. A night street in Miami glows with pink and cyan neon. <Picture 2> is SpongeBob SquarePants (S2) with sunglasses leans against a black muscle car. (S1) Sandy Cheeks <Picture 1> is in an astronaut suit with a fish bowl over her head runs up, holding a hamburger. The camera tracks right with small amplitude at fast speed as she reaches him. She (S1) says in a breathless, sharp voice: [English] They're coming. We gotta move. He (S2) replies in a low, cool voice: [English] Let them come. [Shot 2] At 00:07.000, the camera cuts to a close-up of the hamburger being inserted into a car computer, green code flashing on a tiny screen with the headline "Krabby Patty secret formula". The green laser line sweeps smoothly across the surface of the hamburger, casting a vibrant, neon-glow over the sesame seed bun. As it passes, a digital readout begins to flicker into existence, breaking down the burger's composition in real-time.
overall_soundscape: Car engines idle, distant sirens wail, neon buzzes, and the floppy disk clicks into the drive.
non_diegetic_music: A driving 1980s synthwave track with gated reverb drums, pulsing bass, and a heroic synth lead.
Similar Models
AI Models for Image, Video & Text Generation
nostalgic cinema h3 is a LoRA for the MiniMax H3 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other MiniMax H3 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Text / LLM Models
411
Anima Models
509
Chroma Models
14
Flux Models
1,071
Flux 2 / Klein Models
1,237
MiniMax H3 Models
331
Hunyuan Models
197
Ideogram Models
20
Krea2 Models
674
Qwen Models
17
Qwen2 Models
36
Ltx2 Models
150
Stable Diffusion 1.5 Models
6,465
Stable Diffusion XL 1.0 Models
15,432
Zimage Models
804
Wan Models
919

Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026
