# Recraft V3

> Source: https://aiwiki.ai/wiki/recraft_v3
> Updated: 2026-06-28
> Categories: AI Models, Generative AI, Image Generation
> License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
> From AI Wiki (https://aiwiki.ai), the free encyclopedia of artificial intelligence. Reuse freely with attribution to "AI Wiki (aiwiki.ai)".

Recraft V3 is a text-to-image generation model developed by [Recraft AI](/wiki/recraft_ai) and released on October 30, 2024, that became the first model to reach the number-one position on the Artificial Analysis Text-to-Image leaderboard, surpassing models from Black Forest Labs (FLUX), Midjourney, and OpenAI (DALL-E 3). Built on a 20-billion-parameter architecture trained from scratch and debuting under the internal codename "red_panda," it is designed for professional design work and is distinguished by three capabilities that competing models lacked at launch: native scalable vector graphics (SVG) output, the rendering of long passages of legible text at user-specified positions inside an image, and brand controls such as exact hexadecimal color matching and reusable custom styles. According to Artificial Analysis, Recraft V3 held a leaderboard Elo of approximately 1172 with a 72% win rate at release, and it remained the top-ranked model for roughly five consecutive months. A successor model, Recraft V4, was released in February 2026.

## What is Recraft V3?

Recraft V3 is a [text-to-image](/wiki/text_to_image) model purpose-built for graphic design rather than general image generation. Where most image models are optimized for photorealistic or artistic rendering, Recraft V3 targets the assets a design or marketing team actually ships: logos, icons, posters, packaging, social graphics, and on-brand illustration sets. Its three signature differentiators are native vector (SVG) output, long and positionable in-image text, and brand-fidelity controls (exact colors and reusable styles). Recraft, the company behind the model, frames it as a model that "thinks in design language" rather than one retrofitted for design from a general-purpose architecture.[2]

The model is available through the Recraft web application, iOS and Android apps, and the Recraft API, and it is also distributed on third-party inference platforms such as Replicate and Hugging Face.[1][15]

## Background

[Recraft AI](/wiki/recraft_ai) was founded in 2022 by Anna Veronika Dorogush, a machine learning scientist who had previously co-created the CatBoost gradient-boosting library at Yandex and held roles at Google and Microsoft.[14] The company is described in its own funding announcements and on Wikipedia as London-based, and Dorogush is based in London; some startup directories also list a U.S. (San Francisco) entity.[11][14] Recraft emerged from stealth on May 31, 2023, when it publicly demonstrated vector graphics generation on Product Hunt.[14]

Recraft's founding premise was that existing text-to-image models were not built for professional design work. Tools like DALL-E and Stable Diffusion produced raster images with frequent anatomical errors, no vector support, and limited ability to render readable text inside images. Dorogush set out to build a model trained from the ground up around design requirements rather than retrofitting an existing architecture.

### How is Recraft funded, and how big is it?

The company raised a $12 million Series A from Khosla Ventures in January 2024.[14] In May 2025 it closed a $30 million Series B led by Accel, with participation from Madrona Ventures, RTP Global, and existing investors including Nat Friedman and Elad Gil.[10][11] At the time of the Series B announcement, Recraft reported more than 4 million registered users and over $5 million in annual recurring revenue, with 700% user growth over the prior year.[11] TechCrunch summarized the trajectory bluntly, calling Recraft "the startup behind the image model that beat OpenAI's DALL-E and Midjourney on a respected industry benchmark."[11] The company later reported reaching 7 million users by early 2026.[11]

### Earlier models

Recraft's first publicly available model was released in 2023 alongside the company's Product Hunt launch. In March 2024, the company released Recraft V2 (also called Recraft 20B), described internally as the first model built from scratch to professional design standards.[13] V2 introduced the 20-billion-parameter architecture that V3 would later inherit and expand upon, and demonstrated that a custom-trained model could match or exceed the output of fine-tuned variants of Stable Diffusion and DALL-E 3 on benchmark tasks involving perspective accuracy, quantity representation, and object positioning.[13]

## When was Recraft V3 released, and why was it called "red panda"?

Recraft V3 was released publicly on October 30, 2024.[2] In the days before the official announcement, a mysterious entry labeled "red_panda" appeared at the top of the Artificial Analysis Text-to-Image Arena leaderboard, ranked approximately 40 Elo points ahead of the second-place model.[3] The leaderboard uses a crowdsourced voting method similar to chess Elo ranking: two models receive identical prompts and a human voter selects the better result. Because the submission was anonymous, several AI researchers and journalists speculated publicly about the creator before TechCrunch confirmed on October 28, 2024 that the model belonged to Recraft.[3]

According to Dorogush, the codename came from actual users: during closed testing, people kept generating images of red pandas, which stuck as an informal identifier before the official V3 name was applied.

V3 was trained on Nebius AI infrastructure using a Kubernetes cluster managed via Kubeflow.[7] The training process involved significant engineering challenges. Early runs operated at roughly one-eighth the expected speed due to network bottlenecks affecting GPU-to-GPU gradient synchronization. Recraft and Nebius engineers resolved the problem through GPU Direct RDMA configuration, patched NCCL libraries for collective communications, and a recompilation of PyTorch with static NCCL builds.[7] These changes brought training speed to within approximately six times the original target rather than the full theoretical maximum, but the resulting model achieved state-of-the-art performance on the PartiPrompts benchmark, with over 50% preference against major competitors in head-to-head evaluations.[7]

## How did Recraft V3 perform on the Artificial Analysis leaderboard?

At the time of its release, Recraft V3 held an Elo score of approximately 1172 on the Artificial Analysis Text-to-Image Arena hosted on Hugging Face, with a reported win rate of 72%, according to Artificial Analysis.[4] This placed it ahead of:

| Model | Elo score | Win rate |
|---|---|---|
| Recraft V3 | 1172 | 72% |
| FLUX 1.1 Pro | 1143 | 68% |
| Ideogram v2 | 1102 | 63% |
| Midjourney v6.1 | 1093 | 64% |
| Stable Diffusion 3 Large Turbo | 1084 | 61% |
| DALL-E 3 HD | 984 | 51% |

Recraft V3 held the top position on the leaderboard for five consecutive months following its release.[11] The Artificial Analysis arena uses crowdsourced pairwise comparisons rather than automated metrics, so the scores reflect human aesthetic preferences among the platform's primarily technical user base. The company itself published a comparative analysis noting that its model outperformed FLUX 1.1 Pro, Ideogram v2, and Midjourney v6.1 across categories including image-text consistency, visual quality, and instruction following.[12]

The leaderboard result, achieved by an anonymous model from a low-profile startup, became the model's primary credibility anchor. As TechCrunch reported when announcing the model's identity, a stealth entry had "beat DALL-E and Midjourney on a popular benchmark," which is what drew sustained attention from AI research and design communities.[11]

## What is Recraft V3 good at?

Recraft V3's strengths cluster around the parts of image generation that professional designers, not casual users, care about most: vector output, in-image text, and brand consistency. Each is covered in detail below.

### Native SVG output

One of the most practically significant distinctions of Recraft V3 is its ability to generate native scalable vector graphics directly from a text prompt. Most text-to-image models, including [Midjourney](/wiki/midjourney), DALL-E, Stable Diffusion, and [Flux (text-to-image model)](/wiki/flux), produce raster images. Raster images store pixel data at a fixed resolution and become pixelated or blurry when scaled up.

SVG (Scalable Vector Graphics) files describe images as mathematical paths, shapes, and curves. Because the geometry is defined mathematically rather than as a grid of pixels, SVG images can be scaled to any size without quality loss. This property is essential for logos, icons, and other brand assets that must appear cleanly at both thumbnail and billboard scales.

Recraft V3 generates SVG files through a dedicated vector model variant.[15] The outputs include structured layers and clean geometry. The vector capability spans a range of complexity, from simple monochrome icons and pictograms to detailed multi-color illustrations. Available vector styles include flat vector art, line art, engraving, bold stroke, and over 20 additional substyles.[6]

The limitation is notable: generated SVG files frequently contain excessive anchor points and redundant path segments. Professional designers using V3's vector output for production work have reported spending anywhere from 30 minutes to over an hour cleaning up a single generated file in tools like Adobe Illustrator or Inkscape before it meets the standards required for client delivery. The Recraft team acknowledged this as an area of ongoing improvement, and Recraft V4 (released February 2026) emphasized cleaner SVG geometry as a primary upgrade.[8]

Despite this caveat, no other major text-to-image model at the time of V3's release offered native SVG generation. Recraft V3's vector mode filled a gap that previously required either manual illustration, specialized design software, or post-processing of raster outputs through auto-tracing tools, which produce similarly noisy path data.

### Long text rendering

Text rendering is one of the historically weakest areas across AI image generation. Models like [Midjourney](/wiki/midjourney), DALL-E, and Stable Diffusion regularly produced misspellings, garbled characters, and distorted letterforms even for short words or phrases. FLUX models improved noticeably on this in 2024 but remained inconsistent with sentences longer than a few words.

Recraft V3 introduced a substantially different approach. Recraft describes V3 as "the only model in the world that can generate images with long texts, as opposed to just one or a couple of words."[2] The model can render full sentences and multi-line paragraphs within images, with legible typography that integrates visually with the surrounding composition rather than appearing as a separate overlay.

Beyond legibility, V3 adds positional control: users can specify where text should appear within an image, at what size, and with what approximate style treatment. This positional text placement was unique to Recraft V3 at the time of release; as of early 2026, the Recraft documentation still describes it as the only model with this capability.[1]

Practical applications include:

- Poster and advertisement designs where body copy must be legible
- Social media graphics with captions or calls to action embedded in the image
- Packaging mockups with product names and ingredient lists
- Signage and wayfinding visualizations
- Infographics that combine visual elements with explanatory text

The text rendering capability is available in both raster and vector output modes, though SVG text rendering is generally cleaner because vector paths describe letterforms precisely rather than approximating them as pixel grids.

### Brand controls and style sets

Recraft V3 includes several features aimed at professional brand consistency workflows, which represent a departure from how consumer-oriented models like Midjourney and DALL-E operate.

#### Style library

The model ships with a style library containing over 100 curated styles organized into four main categories:[6]

**Realistic image** styles are intended to produce outputs resembling photographs. Substyles include natural light, studio portrait, enterprise, HDR, hard flash, motion blur, black and white, evening light, faded nostalgia, retro realism, retro snapshot, urban drama, and product photo, among others.

**Digital illustration** styles cover drawn and computer-generated images with simplified or stylized textures. This category contains 46 distinct options including hand-drawn, grain, pixel art, pop art, risograph, clay, pencil sketch, bold sketch, street art, and urban sketching.

**Vector illustration** styles produce flat-color and limited-palette outputs appropriate for icons and scalable graphics. Sub-styles include line art, engraving, and bold stroke.

**Emblem** styles are designed for badge and logo-format outputs, with options including prestige emblem, stamp, punk graphic, and vintage emblem.

The default style for Recraft V3, used when no style is specified, is designated "Recraft V3 Raw." This mode gives the model more latitude in aesthetic decisions rather than constraining output to a specific visual preset.

#### Custom style creation

Users can upload reference images to create a custom style profile. The model extracts the visual characteristics of the reference material and applies them consistently across subsequent generations. This workflow allows a brand team to establish a style template based on existing assets, photography, or illustration work, then generate new images that match that aesthetic without fine-tuning the model's weights. Style creation costs 40 API units ($0.04) per operation.[5]

#### Color control

The API accepts exact hexadecimal color codes as parameters. Images generated with color specifications will use those colors without the color drift that typically occurs when prompts describe colors in natural language. This allows marketing and design teams to maintain brand palette compliance across batches of generated assets.[1]

#### Artistic level parameter

V3 exposes an "artistic level" parameter that adjusts how much creative latitude the model takes with composition and perspective. Lower values produce conventional, expected layouts; higher values result in more unusual angles, cropping, and compositional choices. This parameter gives users a dial between predictable commercial output and more experimental results.[1]

## What is V3 Raw mode?

Recraft V3 Raw is the model's default style, used when no explicit style preset is selected. Unlike named styles that constrain output toward a specific aesthetic category, Raw mode does not enforce a particular visual language. The model makes its own decisions about rendering approach based on the prompt.

In practice, Raw mode tends to produce results that lean toward photorealistic or highly detailed illustration output. It is described in Recraft's documentation as the most versatile option for users who want the model's full range without committing to a style category. For developers using the API, passing no style parameter defaults to V3 Raw behavior.[1]

Raw mode is distinct from the model's photorealism substyles (such as natural light or studio portrait), which actively guide the model toward photographic rendering conventions. Raw mode leaves more decisions to the model's training distribution.

## What is Recraft V4, and how does it differ from V3?

Recraft V4 was released on February 17, 2026, described by the company as a ground-up rebuild focused on what it calls "design taste."[8] The model was developed in close collaboration with professional designers, with training optimized around aesthetic judgment rather than broad visual appeal.

### V4 improvements

V4 offers improved handling of composition, lighting, material surfaces, and spatial depth. The model follows complex positional instructions more reliably than V3, including foreground and background relationships, rule-of-thirds placement, and layered scene construction.[8]

V4's text rendering is sharper than V3, with typography treated as a structural component of the composition rather than an overlay element. The SVG output quality is cleaner, with fewer redundant anchor points, addressing the main criticism of V3's vector files.[8]

A new Exploration Mode generates multiple visual variations from a single prompt, returning a set of options to compare before committing to a refinement direction. Exploration Mode costs 16 credits per generation (2 credits per image across 8 images).[9]

### V4 versions and pricing

V4 is available in four variants:[9]

| Version | Resolution | Generation time | Price (raster) | Price (vector) |
|---|---|---|---|---|
| V4 Standard | 1024x1024 | ~10 seconds | $0.04 | $0.08 |
| V4 Pro | 2048x2048 | ~28 seconds | $0.25 | $0.30 |
| V4 Vector | 1024x1024 | ~15 seconds | N/A | $0.08 |
| V4 Pro Vector | 2048x2048 | ~45 seconds | N/A | $0.30 |

V4 supports multiple output formats: SVG, PNG, JPG, PDF, TIFF, and Lottie (for animated assets). All V4 tiers are available on the Free plan. However, at V4's launch, some V3 features including style creation, prompt-based editing, image sets, and the artistic level parameter were not yet supported in V4.[9]

## How does Recraft V3 compare to Midjourney and Flux?

The following table summarizes the key capability differences between Recraft V3 and major competing image generation models at the time of V3's release:

| Feature | Recraft V3 | [Flux 1.1 Pro](/wiki/flux) | [Midjourney](/wiki/midjourney) V6.1 | [GPT Image 1](/wiki/gpt_image_1) |
|---|---|---|---|---|
| Native SVG output | Yes | No | No | No |
| Long text in images | Yes | Partial (short phrases) | Limited | Partial |
| Text positioning control | Yes | No | No | No |
| Brand color specification | Yes (hex codes) | No | No | No |
| Custom style creation | Yes | No | Limited | No |
| Inpainting/outpainting | Yes | Limited | Yes | Yes |
| API access | Yes | Yes | Yes (alpha) | Yes |
| Raster output | Yes | Yes | Yes | Yes |
| Model size | 20B parameters | ~12B parameters | Undisclosed | Undisclosed |
| Arena ELO (Oct 2024) | 1172 | 1143 | 1093 | 984 (DALL-E 3) |

On aesthetic quality in head-to-head evaluation, Midjourney remains a top choice for artistic and illustrative styles, with particularly strong watercolor and painterly rendering. FLUX 1.1 Pro is generally faster (5-15 second median generation time vs. 7-10 seconds for V3) and is highly regarded for photorealism. GPT Image 1 (released by OpenAI in April 2025 as the successor to DALL-E 3) excels at instruction-following in complex compositional scenarios.

Recraft V3's differentiated position is in the combination of vector output, long text rendering, and brand control tooling, none of which are available together in competing models. As one widely shared review put it, Recraft V3 was "the best AI image generator you never heard of," reflecting the gap between its benchmark standing and its public profile relative to Midjourney and OpenAI.[17]

## How much does Recraft V3 cost?

Recraft V3 is available through the Recraft web application, iOS and Android apps, and the Recraft API. Pricing follows two structures: subscription plans for application users and prepaid API unit packages for developers.

### API pricing

API access uses a credit system where $1.00 purchases 1,000 API units. Units do not expire. Per-operation costs are:[5]

| Operation | Units | USD |
|---|---|---|
| V3 raster image | 40 | $0.040 |
| V3 vector image | 80 | $0.080 |
| V4 raster image | 40 | $0.040 |
| V4 Pro raster | 250 | $0.250 |
| V4 vector image | 80 | $0.080 |
| V4 Pro vector | 300 | $0.300 |
| Style creation | 40 | $0.040 |
| Background removal | 10 | $0.010 |
| Image vectorization | 10 | $0.010 |
| Creative upscale | 250 | $0.250 |
| Crisp upscale | 4 | $0.004 |
| Erase region | 2 | $0.002 |

### Subscription plans

The web application offers monthly and annual subscription tiers. Annual billing reduces cost by 20%. Plan tiers at the time of V3's release included:

| Plan | Monthly price | Monthly image credits |
|---|---|---|
| Free | $0 | 50 images per day |
| Basic | $10 | ~1,000 credits |
| Advanced | $27 | Higher allocation |
| Pro | $60 | ~8,400 images |

Images generated on the Free plan are owned by Recraft, displayed publicly in the community gallery, and do not carry commercial rights. Paid plans grant full ownership and commercial rights and allow private generation.

Subscription credits do not roll over at the end of each billing cycle. Additional credits can be purchased as top-ups. The API uses a separate prepaid unit system and is not tied to the subscription credit pool.

## What is Recraft V3 used for?

### Logos and brand identity

Recraft V3's combination of vector output and color control makes it one of the few AI tools usable early in a logo design process. A designer can generate vector illustrations in multiple styles with exact brand colors, export the SVG files, and begin manual refinement in vector editing software rather than starting from scratch. The workflow does not replace professional logo design, but compresses the ideation and draft generation phase.

### Marketing and advertising assets

The text-in-image capability addresses a longstanding pain point for marketing teams using AI image generation. Social media posts, ad banners, and email headers often require text overlay as part of the design rather than as a separate layer added in post-production. V3 generates the text as part of the initial image, reducing the number of production steps.

### Icon sets and UI illustration

The flat vector and line art styles are suited to icon set production for web and mobile applications. The style library's consistency features allow a team to generate multiple icons in the same visual language without manual matching. The resulting files require cleanup but provide a faster starting point than purely manual work.

### Product mockups

Recraft's canvas includes mockup generation tools that place generated images into product templates such as t-shirts, mugs, and packaging. These are useful for e-commerce sellers and product designers who need to visualize designs on physical objects without photography sessions.

### Batch creative production

The API's style and color controls make V3 suitable for automated batch generation workflows. A team can define a style template once and use the API to generate hundreds of on-brand assets programmatically for use across multiple campaigns or markets.

## How was Recraft V3 received?

Recraft V3's October 2024 launch received substantial coverage after TechCrunch reported the anonymous "red_panda" model's appearance at the top of the Artificial Analysis leaderboard.[3] The unusual route to public attention, appearing pseudonymously on a benchmark before the official announcement, created attention in AI research and design communities.

Joe Penna, a former researcher at Stability AI, publicly praised the model shortly after its reveal: "Wow! Amazing new model, Recraft. I'm very impressed."[17]

Design professionals who tested V3 noted its performance on photorealistic detail. In head-to-head testing, photographer Jenn Mishra found that Recraft "produced more photographically complex images with detailed depth of field and realistic object placement compared to Midjourney." Across design forums and LinkedIn, the most frequently cited workflow benefit was the vector generation capability, with some designers estimating it saved two to four hours per project compared to manual illustration.

The model was noted by TechCrunch, Business Insider, and Decrypt as one of the more surprising releases of late 2024 given Recraft's low public profile relative to Midjourney and OpenAI.[17] The Artificial Analysis leaderboard performance gave the company a credible benchmark anchor that larger, better-known models had not matched.

Recraft V3 remained on the top of the Artificial Analysis leaderboard for five consecutive months, a run that helped the company close its Series B in May 2025.[11]

Enterprise adoption followed the Series B announcement. Recraft reported that Netflix, HubSpot, and Ogilvy were among organizations using the platform. The company reached 7 million users by early 2026, up from 4 million at the Series B.[11]

## What are the limitations of Recraft V3?

### SVG output quality

The main practical limitation of Recraft V3's vector generation is path complexity. Generated SVG files frequently contain redundant anchor points and overlapping path segments that reflect the model's raster-trained underlying architecture rather than a true understanding of vector geometry. Professional designers report spending 30 minutes to over an hour cleaning up a single generated file before it meets production standards. This limits the time savings relative to the idealized workflow.

### Complex multi-element compositions

For scenes involving many distinct objects or precise spatial relationships between elements, V3 can produce inconsistencies in proportions and spatial arrangement. The same prompt may return noticeably different compositional structures across multiple generations, which reduces reliability for workflows that require consistent layouts.

### Photorealism scope

V3's design philosophy prioritizes graphic design accuracy over photorealism as a primary goal. For projects that require true photorealistic output as the main objective rather than brand consistency or vector capability, models like FLUX 1.1 Pro or Midjourney may produce more convincing photographic results for a broader range of subjects.

### Platform reliability

Recraft experienced service reliability issues after V3's launch. Server capacity problems led to erroneous credit deductions for some users between September 2024 and January 2025. In February 2025, a service outage lasting over five days prevented users from accessing generated content; no advance notification was issued. Export and download failures were reported from February through April 2025. These operational issues drew criticism from users who depended on the platform for professional work.

### Free plan restrictions

Images generated on the Free plan are publicly visible and owned by Recraft rather than the user. This limits the platform's usefulness for commercial experimentation without a paid subscription, which is a different policy from competitors like FLUX (where models are available open-source) and Midjourney (where free-tier images are in a community gallery but the user retains rights under certain conditions).

### Mobile performance

The Recraft canvas application performs poorly on mobile devices and low-powered laptops, limiting access for users without desktop workstations or mid-range or higher computers.

## See also

- [Recraft AI](/wiki/recraft_ai)
- [Flux (text-to-image model)](/wiki/flux)
- [Midjourney](/wiki/midjourney)
- [GPT Image 1](/wiki/gpt_image_1)
- [Stable Diffusion](/wiki/stable_diffusion)
- [Ideogram](/wiki/ideogram)
- [DALL-E](/wiki/dall-e)

## References

1. Recraft AI. "Recraft V3 documentation." recraft.ai/docs/recraft-models/recraft-V3. Accessed May 2026.
2. Recraft AI. "Recraft introduces a revolutionary AI model that thinks in design language." recraft.ai/blog/recraft-introduces-a-revolutionary-ai-model-that-thinks-in-design-language. October 30, 2024.
3. Metz, Cade. "A mysterious new image generation model has appeared." TechCrunch. October 28, 2024. techcrunch.com/2024/10/28/a-mysterious-new-image-generation-model-has-appeared/
4. Artificial Analysis. "Text-to-Image Leaderboard." huggingface.co/spaces/ArtificialAnalysis/Text-to-Image-Leaderboard. Accessed May 2026.
5. Recraft AI. "API Reference: Pricing." recraft.ai/docs/api-reference/pricing. Accessed May 2026.
6. Recraft AI. "API Reference: Styles." recraft.ai/docs/api-reference/styles. Accessed May 2026.
7. Nebius AI. "Training a 20B foundational model: Recraft's journey." nebius.com/customer-stories/recraft. Accessed May 2026.
8. Recraft AI. "Introducing Recraft V4." recraft.ai/blog/introducing-recraft-v4-design-taste-meets-image-generation. February 17, 2026.
9. Recraft AI. "Recraft V4 documentation." recraft.ai/docs/recraft-models/recraft-V4. Accessed May 2026.
10. Recraft AI. "Recraft Raises $30M Series B." recraft.ai/news/series-b-announcement. April 30, 2025.
11. Statt, Nick. "A stealth AI model beat DALL-E and Midjourney on a popular benchmark, and its creator just landed $30M." TechCrunch. May 5, 2025. techcrunch.com/2025/05/05/a-stealth-ai-model-beat-dall-e-and-midjourney-on-a-popular-benchmark-its-creator-just-landed-30m/
12. Recraft AI. "Comparing popular and high-performing text-to-image models and providers." recraft.ai/blog/comparing-popular-and-high-performing-text-to-image-models-and-providers. Accessed May 2026.
13. Recraft AI. "Recraft 20B." recraft.ai/blog/recraft-v2. March 13, 2024.
14. "Recraft." Wikipedia. en.wikipedia.org/wiki/Recraft. Accessed May 2026.
15. Replicate. "recraft-ai/recraft-v3-svg." replicate.com/recraft-ai/recraft-v3-svg. Accessed May 2026.
16. DePIN Scan. "Recraft V3: The New Leader in AI Image Generation." depinscan.io/news/2024-11-01/recraft-v3-the-new-leader-in-ai-image-generation. November 1, 2024.
17. Decrypt. "Meet Recraft V3: The Best AI Image Generator You Never Heard Of." decrypt.co/289570/recraft-v3-best-ai-image-generator-you-never-heard-of. Accessed May 2026.