Match the base model
Compare families, versions and availability before choosing a workflow.
LoRA training / FLUX.1 Dev
Build a focused FLUX.1 Dev LoRA dataset.
Prepare a FLUX.1 Dev concept with varied character views, clear captions and a simple evaluation plan. Keep FLUX.1 and FLUX.2 adapter versions separate.
Quick answer: FLUX.1 Dev LoRA training is integrated at 167 credits per task. Prepare images and captions, sign in, and submit when the required services are configured. Generate with the paired model after training succeeds.
Cloud training is integrated for Krea 2, FLUX.1, FLUX.2 Dev, Qwen Image, Z-Image, Wan 2.2 I2V and LTX-2 19B. Configure the required services, sign in and check the quoted credit cost before submitting.
Training dataset
Add images of the style, character or object you want to teach.
Images0 / 30
Avg. shortest edge—
Image captions0 / 0
Files stay in this tab until submission. Cloud training sends your images and captions to WaveSpeed. Reloading clears local files; cloud jobs remain in My LoRAs.
A focused dataset works better
Show the same character from different angles, with different expressions, lighting and backgrounds.
Training capabilities and requirements
Costs and limits below follow the application configuration. Integration describes the code, not verified provider uptime or a successful live training run.
| Model | Integration | Cloud input limits | Credits and settings | Output and compatibility |
|---|---|---|---|---|
| FLUX.1 Dev | Integrated; configuration required | 4–30 JPEG, PNG or WebP images with captions and a trigger phrase. Up to 15 MiB per image; 25 MiB total. | Training: 167 credits / task. Generation: 10 credits / image. Fixed training steps: 500. | LoRA weights after success; use the paired FLUX.1 Dev generator. Compatibility with other base models is not implied. |
Cloud tasks require sign-in and sufficient credits. Krea 2 needs Fal; WaveSpeed image and video trainers need WaveSpeed access and R2 storage.
Cloud training sends your selected media and captions to the provider. Image and video dataset limits differ. Confirm account readiness before submitting.
A focused workflow
A focused workflow for FLUX.1 Dev.
A character dataset should teach identity without tying it to one pose or background. Keep the recognizable features stable while adding useful visual variation.
Inspect the source files
Read real image dimensions and check the local file limits before export.
Review every caption
Describe changing details instead of silently teaching them as part of the concept.
Keep a reusable draft
Export settings and captions together. Source image files stay separate.
Ideas worth teaching
Concept ideas for FLUX.1 Dev.
Explore three ways to define a training concept. Each reference links to a dedicated workflow, with dataset advice and evaluation prompts.
One character. New settings.
An original ceramic explorer gives a dataset a clear identity. Vary the angle, pose and surroundings instead of repeating one composition.
Caption exampleohwx_robot, a ceramic explorer with blue glass eyes, standing beside an alpine lake in daylight.
Explore character LoRA training
A style that travels.
Use this coastal illustration as a visual-language reference. A style dataset should vary the subject while keeping its materials, colors and mark-making coherent.
Caption exampleA coastal village in ohwx_style, gouache texture, warm flat colors and fine ink contours.
Explore style LoRA training
Keep the product recognizable.
A blank amber bottle makes shape and materials easy to discuss. Include alternate views of its glass body and cap rather than teaching a single background.
Caption exampleohwx_bottle, an amber glass bottle with a round walnut cap, on a travertine surface in window light.
Explore product LoRA trainingThese original images were AI-generated as concept references. They are not Loras AI training outputs, before/after comparisons or evidence of model performance.
From intent to evaluation
How to prepare your FLUX.1 Dev concept.
Prepare the image or video dataset required by the selected model, review its trigger and captions, then submit training. Use the completed weights with their matching generator.
- 1
Choose one concept
Decide whether you want a recognizable character, a transferable style, a distinctive product or a specific motion.
Read the note - 2
Collect useful examples
Keep the intended concept consistent while varying details you do not want the model to memorize.
Read the note - 3
Review captions & export
Inspect file dimensions, edit each caption and export the local configuration before leaving the workspace.
Read the note - 4
Plan your test prompts
Test completed, compatible LoRA weights with new prompts. Record the model, settings, successes and failures, and compare with the base model to evaluate the concept.
Read the note
Dataset & compatibility
Build a better FLUX.1 Dev dataset.
Keep the FLUX.1 Dev base version with the adapter and configuration. Do not silently substitute FLUX.2, Kontext or another FLUX family workflow.
Read the dataset preparation note- Keep the same character recognizable in every selected image.
- Vary expression, viewpoint and pose deliberately.
- Change backgrounds so identity is not tied to one location.
- Caption clothing and props that should remain changeable.
Prompt notebook
New-prompt ideas for FLUX.1 Dev.
Save these ideas for evaluating a compatible trained adapter later. They are prompt examples, not generated results or a promise of consistent output.
A different environment
ohwx_robot exploring a quiet greenhouse, three-quarter view, soft morning light.
A new action
ohwx_robot opening a small field notebook beside a mountain trail, full-body composition.
A closer view
A close-up portrait of ohwx_robot, blue glass eyes, plain warm gray background, soft studio light.
Changing the light
ohwx_robot standing on a wooden pier at blue hour, gentle reflections, wide composition.
A simple baseline
ohwx_robot standing on a neutral background, front view, even lighting, no other objects.
A new composition
ohwx_robot sitting beside a large fern leaf, low camera angle, natural daylight.
Related notes
A little preparation goes a long way.
Practical reading on image selection, captions, training settings and evaluating what a model actually learned.
How many images do you need?Choose useful variation rather than relying on one universal image count.A practical LoRA captioning guideSeparate the concept from changing details, with character, style and product examples.Training steps without the guessworkUnderstand steps, learning rate and overfitting before changing advanced settings.How to evaluate a trained LoRATest new prompts, compare a baseline and document useful failures.
FAQ
FLUX.1 Dev: questions before you train.
Model-specific guidance, with the current availability stated clearly.
What should I prepare for FLUX.1 Dev?
A character dataset should teach identity without tying it to one pose or background. Keep the recognizable features stable while adding useful visual variation. Keep the FLUX.1 Dev base version with the adapter and configuration. Do not silently substitute FLUX.2, Kontext or another FLUX family workflow.
How should I evaluate a FLUX.1 Dev concept?
Try new poses, backgrounds and lighting. Compare recognizable identity against a baseline rather than judging only a recreation of a training image.
Can I submit a paid training job on this page?
Krea 2, FLUX.1, FLUX.2 Dev, Qwen Image, Z-Image, Wan 2.2 I2V and LTX-2 19B have training and paired generation integrations. Paid tasks require configured services, sign-in and sufficient credits. Other catalog models remain previews.
What happens to the images I add?
Local draft preparation processes images in the current browser tab; exported JSON excludes source files. Refreshing or leaving clears local images. Submitting cloud training sends the selected dataset and captions to the provider; WaveSpeed training also uses configured R2 storage for datasets and archived artifacts. Storage privacy depends on bucket access settings. Generation sends prompts and selected LoRA references to the relevant service. Only submit material you have permission to use.
Can I reuse one LoRA with every image or video model?
Adapters are not interchangeable. Match the model architecture, base version and loading workflow. Krea 2, MOSS and Anima need their own compatible weights; similar names do not imply compatibility. Video workflows may also require multiple adapter files.
Keep exploring
Find a compatible next step.
Compare related model families before choosing a training workflow. Adapter formats and base-model versions must remain compatible.
Your FLUX.1 Dev concept starts here.
Choose a compatible model, prepare images and captions, then submit an available training or generation workflow. You can also export a dataset configuration draft for free.