Image Editing
Edit instruction
“Change the scene to night: a deep, dark sky with subtle, glistening stars visible behind the mountain.”
Reve AI's text-to-image generation model with strong aesthetic quality, accurate text rendering, and detailed instruction following capabilities
Details
Model ID
reve
Also known as:
reve-image-1
Creator
Family
reve
Tags
image-generation
text-to-image
image-editing
typography
Starting from
$0.040
/image
via fal.ai, Replicate
Prices shown are in USD
See all providersProvider Performance
Fastest generation through fal at 19,546ms median latency with 100.0% success rate.
Aggregated from real API requests over the last 30 days.
Generation Time
fal
19,546ms
p95: 22,186ms
Success Rate
fal
100.0%
11 / 11 requests
Time to First Byte
fal
18,797ms
p95: 22,574ms
Provider Rankings
| # | Provider | p50 Gen Time | p95 Gen Time | Success Rate | TTFB (p50) |
|---|---|---|---|---|---|
| 1 | fal | 19,546ms | 22,186ms | 100.0% | 18,797ms |
Data updated every 15 minutes. Based on all API requests through Lumenfall over the last 30 days.
Providers & Pricing (4)
Reve Image 1.0 is available from 4 providers, with per-image pricing starting at $0.04 through fal.ai.
All modes
fal.ai
Text to Image
fal/reve
Provider Model ID:
fal-ai/reve/text-to-image
$0.040
/image
fal.ai
Image Edit
fal/reve-edit
Provider Model ID:
fal-ai/reve/edit
$0.040
/image
Replicate
Text to Image
replicate/reve
Provider Model ID:
reve/create
Output
Image
$0.040
per image
Pricing Notes (2)
- • Text-to-image generation with editing capabilities
- • Preserves spatial relationships and structure
View official pricing
• As of
Replicate
Image Edit
replicate/reve--edit
Provider Model ID:
reve/edit
Output
Image
$0.040
per image
Pricing Notes (1)
- • Image editing endpoint for the Reve model
View official pricing
• As of
reve-image-1 API OpenAI-compatible
Lumenfall provides programmatic access to Reve Image 1.0 via a unified OpenAI-compatible API, allowing developers to generate high-fidelity images and perform complex image editing through a single integration. Integrate Reve AI's text-to-image capabilities into any workflow using standard HTTP requests for visual media production.
Base URL
https://api.lumenfall.ai/openai/v1
Model
reve
Code Examples
Text to Image
/v1/images/generationscurl -X POST \ https://api.lumenfall.ai/openai/v1/images/generations \ -H "Authorization: Bearer $LUMENFALL_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "reve", "prompt": "", "size": "1024x1024" }'# Response:# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }import OpenAI from 'openai';const client = new OpenAI({ apiKey: 'YOUR_API_KEY', baseURL: 'https://api.lumenfall.ai/openai/v1'});const response = await client.images.generate({ model: 'reve', prompt: '', size: '1024x1024'});// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }console.log(response.data[0].url);from openai import OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://api.lumenfall.ai/openai/v1")response = client.images.generate( model="reve", prompt="", size="1024x1024")# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }print(response.data[0].url)Image Edit
/v1/images/editsParameter Reference
Required
Supported
Not available
Core Parameters
| Parameter | Type | Description | Modes |
|---|---|---|---|
prompt
|
string | Required. Text prompt for image generation |
T2I
Edit
|
seed
|
integer | Random seed for reproducibility |
T2I
Edit
|
Size & Layout
| Parameter | Type | Description | Modes |
|---|---|---|---|
size
|
string |
Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9")
1365x768
768x1365
1254x836
836x1254
887x1182
1024x1024
1183x887
WxH determines both shape and scale (aspect_ratio and resolution are ignored when size is provided). W:H format is equivalent to aspect_ratio.
|
T2I
Edit
|
aspect_ratio
|
string |
Aspect ratio of the output image (e.g. "16:9", "1:1")
9:16
2:3
3:4
1:1
4:3
3:2
16:9
Controls shape independently of scale. Use with resolution to control both. If size is also provided, size takes precedence. Any ratio is accepted and mapped to the nearest supported value.
|
T2I
Edit
|
resolution
|
string |
Output resolution tier (e.g. "1K", "4K")
1K
Controls scale independently of shape. Higher tiers produce larger images and cost more. If size is also provided, size takes precedence for scale. Any tier is accepted and mapped to the nearest supported value.
|
T2I
Edit
|
1K 7 sizes
| Output |
size
|
aspect_ratio
+
resolution
|
|
|---|---|---|---|
| 1183 × 887 | "1183x887" |
or |
"4:3"
+
"1K"
|
| 1024 × 1024 | "1024x1024" |
or |
"1:1"
+
"1K"
|
| 887 × 1182 | "887x1182" |
or |
"3:4"
+
"1K"
|
| 836 × 1254 | "836x1254" |
or |
"2:3"
+
"1K"
|
| 1254 × 836 | "1254x836" |
or |
"3:2"
+
"1K"
|
| 768 × 1365 | "768x1365" |
or |
"9:16"
+
"1K"
|
| 1365 × 768 | "1365x768" |
or |
"16:9"
+
"1K"
|
How these parameters work
size
Exact pixel dimensions
"1920x1080"
aspect_ratio
Shape only, default scale
"16:9"
resolution
Scale tier, preserves shape
"1K"
Priority when combined
size
›
aspect_ratio + resolution
›
aspect_ratio
›
resolution
size is most specific and always wins. aspect_ratio and resolution control shape and scale independently.
How matching works
Shape matching
– we pick the closest supported ratio.
Ask for
7:1 on a model with
4:1 and 8:1,
you get 8:1.
Scale matching
– providers use different tier formats:
K tiers (
0.5K 1K 2K 4K)
or megapixel tiers (0.25 1).
If the exact tier isn't available, you get the nearest one.
Dimension clamping
– if a model has pixel limits, we clamp dimensions to fit and keep the aspect ratio intact.
Media Inputs
| Parameter | Type | Description | Modes |
|---|---|---|---|
image
|
file |
Required.
Input image(s) to edit
Supports PNG, JPEG, WebP.
|
T2I
Edit
|
Output & Format
| Parameter | Type | Description | Modes |
|---|---|---|---|
response_format
|
string |
How to return the image
url
b64_json
Default:
"url" |
T2I
Edit
|
output_format
|
string |
Output image format
png
jpeg
gif
webp
avif
Gateway converts to requested format if provider doesn't support it natively.
|
T2I
Edit
|
output_compression
|
integer | Compression level for lossy formats (JPEG, WebP, AVIF) |
T2I
Edit
|
n
|
integer |
Number of images to generate
Default:
1Gateway generates multiple images in parallel even if provider only supports 1.
|
T2I
Edit
|
Additional Parameters
| Parameter | Type | Description | Modes |
|---|---|---|---|
sync_mode
fal
|
boolean | If `True`, the media will be returned as a data URI and the output data won't be available in the request history. |
T2I
Edit
|
version
replicate
|
string |
The specific model version to use when generating the image
latest
latest-fast
reve-create@20250915
reve-edit-fast@20251030
reve-edit@20250915
|
T2I
Edit
|
Parameter Normalization
How we handle parameters across different providers
Not every provider speaks the same language. When you send a parameter, we handle it in one of four ways depending on what the model supports:
| Behavior | What happens | Example |
|---|---|---|
passthrough |
Sent as-is to the provider | style, quality |
renamed |
Same value, mapped to the field name the provider expects | prompt |
converted |
Transformed to the provider's native format | size |
emulated |
Works even if the provider has no concept of it | n, response_format |
Parameters we don't recognize pass straight through to the upstream API, so provider-specific options still work.
Reve Image 1.0 Benchmarks
Reve Image 1.0 maintains a competitive position in the text-to-image arena with an Elo rating of 1204 and ranks 15th overall for image editing tasks. In standardized head-to-head comparisons, the model achieved an Elo of 1171 specifically for visual modification capabilities.
Lumenfall Arena
#26
Text-to-Image
1195
Elo
Lumenfall Arena
#14
Image Editing
1187
Elo
Text-to-Image Landscape
Elo vs Cost
1 model without pricing omitted
Elo vs Speed
8 models waiting for enough speed data
Image Editing Landscape
Elo vs Cost
Elo vs Speed
1 model waiting for enough speed data
Competition Results
Image Editing
Edit instruction
“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”
Image Editing
Edit instruction
“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”
Image Editing
Edit instruction
{
"action": "image_edit",
"reference": "uploaded neutral portrait",
"change": "Warm genuine Duchenne smile: lips curved up, slight natural teeth, soft eye crinkles, subtle cheek raise",
"details": "Realistic smiling skin (dimples if present, soft cheek shadows), slightly brighter eyes; keep exact eye shape/color/iris",
"preserve_exact": "Face identity/structure, eyes/nose/lips/eyebrows, hair, skin texture/pores/freckles, makeup, clothing, head pose, background, lighting, shadows, framing",
"no_changes": "No face shape change, no new features, no gaze shift, no hair/clothing/lighting/background edits",
"style": "Ultra-photorealistic 8K portrait, sharp face focus, natural soft lighting, realistic skin glow"
}Text-to-Image
Prompt
“Create a clean, modern vector infographic poster about the Apollo 11 mission. NASA-inspired palette (navy, white, muted red, light gray). Flat-vector style, crisp lines, consistent iconography, subtle gradients only. Steps (stop at landing): 1. Launch (Saturn Vicon) 2. Earth Orbit (Earth + orbit ring icon) 3. Translunar (trajectory arc icon) 4. Lunar Orbit (Moon + orbit ring icon) 5. Descent (lunar module descending icon) 6. Landing (lunar module on the surface icon) Small supporting elements (minimal text): • Crew strip: three silhouette icons with only last names: Armstrong, Aldrin, Collins. • Landing site marker: Moon pin labeled "Tranquility" only. Layout constraints: generous margins, large readable labels, clean background with subtle stars. Vector-only, print-poster look, high resolution.”
Image Editing
Source
Edit instruction
“Transform this photo into a Studio Ghibli–inspired illustration. Use soft pastel colors, hand-painted textures, gentle lighting, dreamy backgrounds, and a warm, nostalgic mood”
Image Editing
Edit instruction
“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”
Image Editing
Edit instruction
{
"action": "image_edit",
"reference": "uploaded neutral portrait",
"change": "Warm genuine Duchenne smile: lips curved up, slight natural teeth, soft eye crinkles, subtle cheek raise",
"details": "Realistic smiling skin (dimples if present, soft cheek shadows), slightly brighter eyes; keep exact eye shape/color/iris",
"preserve_exact": "Face identity/structure, eyes/nose/lips/eyebrows, hair, skin texture/pores/freckles, makeup, clothing, head pose, background, lighting, shadows, framing",
"no_changes": "No face shape change, no new features, no gaze shift, no hair/clothing/lighting/background edits",
"style": "Ultra-photorealistic 8K portrait, sharp face focus, natural soft lighting, realistic skin glow"
}Text-to-Image
Prompt
“Close portrait of a battle-worn paladin in ornate engraved plate armor, hair braided with small beads, faint scars and dirt on the skin, warm torchlight reflecting off metal, shallow depth of field, bokeh sparks, lifelike eyes, highly detailed texture on leather straps and cloth underlayer.”
Uncategorized
Text-to-Image
Prompt
“A glass cube on a wooden table. Inside the cube is a small blue sphere. On top of the cube sits a red book. A green plant is behind the cube, partially visible through the glass. Soft window light from the left.”
Text-to-Image
Prompt
“Create a clear, 45° top-down isometric miniature 3D cartoon scene of Japan's signature dish: sushi, with soft refined textures, realistic PBR materials, gentle lighting, on a small raised diorama base with minimal garnish and plate. Solid light blue background. At top-center: 'JAPAN' in large bold text, 'SUSHI' below it, small flag icon. Perfectly centered, ultra-clean, high-clarity, square format.”
Image Editing
Source
Edit instruction
“Create a caricature of me and my job. Make it exaggerated and humorous, incorporating my profession as a tv show anchor and my love for dogs and hockey.”
Text-to-Image
Prompt
“Hyper-photorealistic interior of a lush Victorian glass greenhouse filled with exotic tropical plants, vibrant blooming orchids, tall ferns, colorful butterflies in flight, sunlight filtering through ornate glass roof creating realistic caustics and dew on leaves, intricate iron framework visible, misty atmosphere, 8K masterpiece.”
3 attempts – showing best result
Text-to-Image
Prompt
“Close portrait of a battle-worn paladin in ornate engraved plate armor, hair braided with small beads, faint scars and dirt on the skin, warm torchlight reflecting off metal, shallow depth of field, bokeh sparks, lifelike eyes, highly detailed texture on leather straps and cloth underlayer.”
3 attempts – showing best result
Top Matchups
See how Reve Image 1.0 performs head-to-head against other AI models, ranked by community votes in blind comparisons.
vs Stable Diffusion 3.5 Large
Challenge: Apollo 11: Journey to Tranquility
25% W · 75% L
vs Nano Banana
Challenge: Bald man challenge
0% W · 100% L
vs Nano Banana 2
Challenge: Over-the-top cartoon caricature
0% W · 100% L
vs Nano Banana
Challenge: Neutral Expression to Genuine Smile
0% W · 100% L
vs GPT Image 1.5
Challenge: Night Sky Transformation
100% W · 0% L
Use Cases
See all Use CasesThe model demonstrates its strongest performance in the anime category, securing rank 5 out of 13 with a 52.4% win rate. It shows lower proficiency in text rendering and photorealism, where it currently ranks near the bottom of performance leaderboards with win rates below 20%.
Gallery
View all 17 imagesReve Image 1.0 FAQ
How much does Reve Image 1.0 cost?
Reve Image 1.0 starts at $0.04 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.
How do I use Reve Image 1.0 via API?
You can use Reve Image 1.0 through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "reve". Code examples are available in Python, JavaScript, and cURL.
Which providers offer Reve Image 1.0?
Reve Image 1.0 is available through Replicate and fal.ai on Lumenfall. Lumenfall automatically routes requests to the best available provider.
Overview
Reve Image 1.0 is a high-fidelity text-to-image model developed by Reve AI that prioritizes visual aesthetics and precise instruction adherence. Unlike many early-generation diffusion models that struggle with complex prompts, Reve 1.0 is engineered to maintain high compositional integrity and detailed attribute mapping. It is particularly distinctive for its ability to render legible, accurate typography directly within generated images.
Strengths
- Typography and Text Rendering: The model excels at embedding clear, correctly spelled text into images, making it suitable for graphic design assets, logos, and posters.
- Instruction Following: It demonstrates a high degree of sensitivity to complex, multi-part prompts, accurately placing objects and applying specific colors or textures as described.
- Aesthetic Quality: The model produces outputs with a polished, professional look, showing particular strength in lighting, skin textures, and balanced photographic compositions.
- Multimodal Input: It supports both text-to-image and image-to-image workflows, allowing for fine-grained control over layout and style through reference images.
Limitations
- Computational Cost: With a starting price around $0.04 per generation, it carries a higher per-image cost than many standard open-weights models or optimized distilled versions.
- Anatomical Edge Cases: While highly capable, it may still produce artifacts in complex human poses or high-density crowd scenes, similar to other models in the current diffusion generation.
- Inference Latency: Given its focus on high-detail output and aesthetic quality, it may have a longer generation time compared to “turbo” or lightning-fast latent consistency models.
Technical Background
Reve Image 1.0 is a diffusion-based model designed around a large-scale transformer architecture optimized for visual-textual alignment. While specific architectural details are proprietary, its training pipeline emphasizes high-quality captioned datasets to improve the semantic connection between user prompts and pixel generation. The model utilizes advanced sampling techniques to achieve its signature sharpness and textural detail.
Best For
This model is best suited for professional creative workflows where visual fidelity and typographic accuracy are non-negotiable, such as social media marketing, UI/UX concepting, and digital illustration. It is a strong choice for users who need a “first-shot” generation that requires minimal post-processing or manual image editing to fix text errors. Reve Image 1.0 is available through Lumenfall’s unified API and playground, allowing developers to integrate its high-aesthetic outputs into their own applications alongside other leading generative models.
Try Reve Image 1.0 in Playground
Generate images with custom prompts — no API key needed.